frank-secondary: swap Swift-1.5 RCO-IQ3_XXS -> Gemma4-26B-A4B QAT Q4_K_M

Payload: HauhauCS/Gemma4-26B-A4B-QAT-Uncensored Q4_K_M (16,796,015,520 B) + the publisher's BF16 mmproj, /home/dank/models/Gemma4-26B-A4B/. Shape: ONE 200,704-token slot (--parallel 1; 2x200,704 does not fit the 24 GiB card), f16 K + q8_0 V under flash attention, batch 4096 / ubatch 1024, --log-verbosity 4, MTP OFF (the gemma4-assistant file is on disk, not loaded: its draft KV is built against the target's full window, measured +1.9 GiB -> 23,806/319 free, no margin beside the f16-K raise). Measured boots (nvidia-smi): q8_0 K + q8_0 V / ubatch 2048 / MTP off = 21,890 used / 2,235 free; with the MTP assistant = 23,806 / 319. Engine facts recorded: gemma4 hybrid attention (25 sliding-window + 5 full-attention layers) so KV scales with 5 layers only, and attention_k_eq_v is honoured by build 5fc4f3c (pool bills K-only; the measured q8_0 pool = 2.05 GiB = the K-only figure). Serve script gained VERBOSITY (+ --log-verbosity in the argv), the SPEC_DRAFT_FILE drafter path, and defaults/lore retargeted to Gemma4. deploy-remote.sh payload gates follow the env. The frank-secondary bats seam is rewritten for the new contract (argv-based) and fixes a pre-existing vacuity: serve_argv regenerates the test env, so mutations made before it were silently undone - tests that mutate now exec through run_stage. frank-secondary is the fleet compaction hub (200,704 is the only window that fits a worst-case compaction input).
2026-10-07 13:48:54 -07:00
parent 5b7b3ccb90
commit 68a525740d
8 changed files with 335 additions and 222 deletions
@@ -27,7 +27,7 @@ merge absorbed the former `vllmScripts` repo, history preserved).
 |--------|---------|---------|-------|------|
 | Dankserver | `frank-primary` | **radiance** (StillDeadcode v1.0.7 line; image `stilldeadcode/radiance@sha256:4c3f484564…` digest-pinned INDEX digest, 287 MiB, `libr4d` gfx1201 kernels, plain `podman run`, root systemd unit) | `Qwen/Qwen3.8-Flash-Next-FP8` official (172.8 GB, 131 shards, sha256-verified) converted **no-recipe** to `qwen4exp-fp8-native.rad` (177,109 MiB measured = 173.0 GiB) — **native modelopt block-FP8, no requantisation** — on **BOTH R9700s TP=2** (`--tp-wire wht6`), experts in a **40 GiB/rank pinned host pool** + VRAM cache (`--placement expert_tiered`, `--expert-vs-cache-ratio 0.82` = the 99 %-hit point), **PLE 47.7 GiB pinned to host RAM** (`--ngram-placement ram`; root unit + `LimitMEMLOCK=infinity`), **fp8 KV 7.32 KiB/token**, **MTP spec decode depth 3**, *…
 | Dankclaw | `frank-large` | **halogen-flash-server 0.16.2** (`ghcr.io/peonist-ai/halogen-flash-server@sha256:0c61bf84…`, digest-pinned, plain `podman run` via `scripts/serve-frank-large.sh`, root systemd unit) | Quat3rnion/halogen-swift1.5-qwen3.8-flash-next-v2-abliterated **`qwen38-flash-next-v2-swift15-abliterated.hgn`** (66,687,678,464 B = compacted r2 of the card's 89,775,868,032 B original, ~62 GiB resident; the v2 `.hgn` format loads in NO other engine), **+ REQUIRED `qwen38-flash-next-ngram.hgn`** (51,200,246,144 B, peonist @5cc17cea — read beside the checkpoint) **+ vision tower** (897,916,416 B, @e053f488 — **vision ON**, `image_url` parts only, ≥256 px probes), **MTP spec decode ALWAYS-ON (`HALOGEN_SPEC_ADAPT=0` — the adaptive default disables the head per request and HALVES decode)**, MTP head INSIDE the checkpoint (`HALOGEN_MTP_HEAD` unset; no sidecar fetched), **2 slots × 200,192 ctx** (KV pool 400,384 positions ≈ 10.7 GiB at ~28 KiB/position; the 27B slots>1-disables-drafting law does NOT carry over — batching and speculation coexist, the card's quickstart ships 2 with the head), **server-side sampler 1.0/0.95/20** (card recipe; models.yml extraBody matches), coupled cap/timeout 65536/7200, prompt cache ON by default (warm 100k turn ≈ 2 s vs ≈ 88 s cold) | 7770 |
-| Dankclaw | `frank-secondary` | llama.cpp master (0.5.0-dev, commit `5fc4f3c`), CUDA sm_86 build (root systemd unit, relinked) | ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF **RCO-IQ3_XXS -mtp** (27B dense qwen3_5 hybrid, 10,442,827,392 B; a per-tensor allocation mix of stock types; the MTP head in the file **drafted** — **spec ON** (draft-mtp depth 3) since 2026-10-06 evening, ngram skipped on the recurrent-rollback law) + the publisher's own **BF16 mmproj** for **vision**, on the RTX 3090, **2 × 114,688** (Frank's 112k cap each since the 2026-10-06 late reshape, cut from 131,072 to fund the **ubatch ladder 512 → 1024 → 2048** — **1,005 MiB free at boot, 763 settled after a vision probe** (encoder buffers resident)) with **q8_0 K + q8_0 V (FP8 class, 34 KiB/token)** under flash attention, batch 4096 / **ubatch 2048** (the ceiling for this shape — 4096 would not fit); **prefill 1,209 t/s @ 3,760 tokens; ~52–58 t/s recipe decode** (MTP acceptance 34–54 %, temp-1.0 noise; decode is ubatch-invariant). Renamed from `frank-small` 2026-10-06 (87721ab). Supersedes the same-morning IQ3_S-mtp payloads: the two-slot no-spec shape and the one-slot MTP shape (both 2026-10-06; payload on disk).|7771|
+| Dankclaw | `frank-secondary` | llama.cpp master (0.5.0-dev, commit `5fc4f3c`), CUDA sm_86 build (root systemd unit, relinked) | HauhauCS/Gemma4-26B-A4B-QAT-Uncensored **Q4_K_M** (25.2 B-param MoE, ~4 B active, 16,780,192,888 B reported by the engine; 30 layers = 25 sliding-window + 5 full-attention) + the publisher's own **BF16 mmproj** for **vision**, on the RTX 3090, **ONE 200,704-token slot** (`--parallel 1`; two 200,704 slots do not fit 24 GiB), **f16 K + q8_0 V** under flash attention (the file declares `attention_k_eq_v` and this build honours it — the pool bills K-only), batch 4096 / **ubatch 1024**, `--log-verbosity 4`, **MTP OFF** (the assistant is a SEPARATE file and its draft KV is built against the target's full window — 23,806 / 319 MiB free with it loaded, no margin beside the f16-K raise). Measured q8_0-K boot: **21,890 used / 2,235 free**. Cutover 2026-10-07 from Swift-1.5 RCO-IQ3_XXS 2×114,688. All three endpoints route harness **compaction** here. | 7771 |

 Retired endpoints (`frank-npu`, and every prior runtime) are in
 the [runbook index](#runbook-index). The full swap history lives in
@@ -308,9 +308,10 @@ image]`) — `frank-large` returned to vision with the flash-server v2 swap
 27-layer Qwen-VL tower — patching, pad-token expansion and 3-part rotary
 are the engine core; `--mm-max-patches` available),
 and `frank-secondary` through
-the publisher's own `mmproj-BF16.gguf` passed as `--mmproj` — the Swift
+the publisher's own BF16 mmproj passed as `--mmproj` — the Gemma4
 GGUF itself carries no vision tensors. `frank-secondary`'s `contextWindow` is
-**114688** (cut from 131072 on 2026-10-06 late to fund the ubatch ladder to 2048), the
+**200704** (the one-slot window since the 2026-10-07 Gemma4 swap; `--parallel 1`,
+so the pool IS the conversation), the
 per-slot window, not the model's native 262144: the harness must compact
 before llama.cpp answers a longer prompt with a 400. Note also
 that
@@ -417,89 +418,63 @@ that (`scripts/build-rocmfpx.sh`, pin `36e9acd`) is untouched.
 `/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server`,
 `GGML_CUDA_FA_ALL_QUANTS=ON`) as a **root systemd unit**
 (`scripts/frank-secondary.service`, `relink_unit`ed into
-`/etc/systemd/system/`), serving `ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF`
-at **RCO-IQ3_XXS -mtp** (10,442,827,392 B, sha256 `e13d3e74…`) **plus
-the publisher's own `mmproj-BF16.gguf`** (931,145,888 B, sha256
-`19acd7fc…`), both `/home/dank/models/Swift15-UncIQ3XXS/`, on port 7771.
-Cutover 2026-10-05 (evening) on Frank's explicit contract: **128k
-context cap, KV at FP8, vision on, as many 128k contexts as fit**;
-reshaped three times on 2026-10-06 — morning to two 131,072 slots
-no-spec, evening to this UNCERSED RCO-IQ3_XXS payload with MTP back
-on, late the RENAME to **frank-secondary** (87721ab) at two 114,688
-slots with the ubatch ladder climbing 512 → 1024 → 2048 (f2575a1,
-d8da7a9). The
-same-day payloads it supersedes: the LIVE MiMo-V2.6 Q6_K shape and the
-Ornith-1.5-9B Q8_0 swap that was committed (77decb5..380aafa) but never
-deployed (blocked at the docs gate; the docs debt is what this section
-settles).
+`/etc/systemd/system/`), serving
+`HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP` at
+**Q4_K_M** (16,796,015,520 B on disk; the engine reports
+16,780,192,888 B, 25,233,142,046 params, vocab 262,144) **plus the
+publisher's own BF16 mmproj** (1,194,827,776 B), both
+`/home/dank/models/Gemma4-26B-A4B/`, on port 7771. Cutover 2026-10-07
+from the Swift-1.5 RCO-IQ3_XXS 2×114,688 shape. The MTP assistant
+(`mtp-gemma-4-26B-A4B-it.gguf`, 251,937,728 B) is on disk, **not loaded**.

-**Architecture: qwen3_5 hybrid, bigger** — block_count 65 (64 real layers +
-the blk.64 MTP head), `full_attention_interval 4` ⇒ **16 full-attention +
-48 Gated DeltaNet**, native 262,144 window, dense. KV exists only in the 16
-attention layers (4 KV heads × 256 dim): 64 KiB/token at f16, **34 KiB/token
-at q8_0**. The DeltaNet state is a fixed per-slot buffer (~150 MiB/slot at
-48 linear layers × 48 value heads). Header facts were read from the Hub
-file by HTTP range + struct parse before anything was downloaded.
+**Architecture: gemma4 MoE hybrid** — 30 layers, 128 experts (8 active),
+n_embd 2816, native 262,144 window. Attention is hybrid: **25
+sliding-window layers (window 1024, a fixed ring each) + 5 full-attention
+layers (5, 11, 17, 23, 29)**, 8 KV heads × 256 dim — so the KV pool scales
+with the 5 full layers ONLY: ~10.6 KiB/token at q8_0, ~20.5 KiB/token at
+f16. `attention_k_eq_v: True` — `gemma4.cpp` maps the absent `wv` to
+`Vcur = Kcur`, and this build's KV cache honours it (no V slots allocated:
+the q8_0 pool measured ~2.05 GiB at 200,704, the K-only figure). **Bill
+K-only.**

-**The shape (2026-10-06 midnight; Frank's tight-fit order, MTP back on
-in the evening, per-slot cut + ubatch climbed to 2048):** `--ctx-size
-229376 --parallel 2` = **TWO 114,688-token conversations** (Frank's
-112k cap each; `n_ctx_slot = CTX_SIZE / PARALLEL`; cut from 131,072 to
-fund the ubatch rungs), `--flash-attn on` pinned, **q8_0 K + q8_0 V**
-(llama.cpp's FP8 class — no true fp8 KV dtype exists; 8.5 effective
-bits; supersedes the same-day f16/f16 rule written for the Ornith 9B
-fit), all layers on the GPU, `--mmproj` for vision, batch 4096 /
-ubatch 2048. **Speculative decoding is ON** (draft-mtp, depth 3): the
-mtp file's head is drafted against the main model's own weights;
-ngram-mod skipped on purpose — on a qwen35 hybrid ngram disables
-recurrent-state rollback, so a rejected draft corrupts the DeltaNet
-state.
+**The shape (2026-10-07):** `--ctx-size 200704 --parallel 1` = ONE
+conversation (Frank's 200k cap; the harness `contextWindow` quotes
+200704), `--flash-attn on`, **f16 K + q8_0 V** (exact K, FP8-class V),
+batch 4096 / **ubatch 1024** (cut from 2048 to fund the f16-K raise),
+`--log-verbosity 4` (debug — the KV/buffer forensics land in the journal),
+`--mmproj` for vision, **speculative decoding OFF** (`SPEC_TYPE=none`).

-**Measured at the midnight boot (2026-10-06, 2 × 114,688 / ubatch
-2048): 23,120 used / 1,005 MiB free, settling 763 MiB after a vision
-probe** (`nvidia-smi` free; the encoder buffers stay resident on this
-boot) — the per-slot cut freed ~1.05 GiB of KV and both ubatch rungs
-spent it back (~0.3 + ~0.75 GiB measured; the 1024 rung had landed
-22,374/1,751, the 2048 rung cost 746 MiB, ~130 over the 616 the rung
-measured on the MiMo shape). The MTP draft ctx costs **~2.4 GiB
-measured** (23,636 − 22,728 + 1,561 at the 262,144 draft window) — ~6×
-the ~0.4 GiB the one-slot era assumed, because the drafter's KV is
-built against the target's FULL context, not the 3-token proposal
-depth; the lighter RCO-IQ3_XXS quant (−1.56 GiB vs IQ3_S-mtp) funds it.
-**Prefill 1,209 t/s @ 3,760 tokens; decode 52.0–58.2 tok/s (recipe
-temp 1.0) / 66.9 (temp 0)**, acceptance 34.2–54.4 % — decode is
-ubatch-invariant, the spread is temp-1.0 acceptance noise.
-`reasoning_effort` probe unchanged: `xhigh` 200, `high` → 500 Jinja
-raise (the models.yml fold stays mandatory).
+**Why MTP is off**: Gemma4's MTP is a SEPARATE assistant file (arch
+`gemma4-assistant`), not an in-file head, and the draft context is built
+against the target's FULL window — measured cost **~1.9 GiB** (23,806 used
+/ 319 free with the assistant loaded, vs 21,890 / 2,235 without). The
+assistant also warns `n_ctx_seq (200704) > n_ctx_train (131072)` — the
+draft runs 53 % past its trained window. The q8_0-K boot leaves 2,235 MiB,
+which the f16-K raise (+2.05 GiB) spends; MTP and exact-K cannot coexist on
+this card.

-**Vision with the publisher's own projector**: ajgazin's repo SHIPS
-`mmproj-BF16.gguf` in the same repo (the IQ3_S era's unsloth mmproj was
-built from the SHARED BASE `Qwen/Qwen3.8-27B`, legal because Swift-1.5's
-vision stack was hash-proven byte-identical to the base). The probe
-traps carry over: ≥256 px probe images or the model answers "video";
-only the OpenAI `image_url` content part reaches the model. **New on
-this payload: the uncensored model thinks more than the censored
-Swift 1.5** — a 64-token budget is eaten entirely by
-`reasoning_content` (empty `content`); 128 tokens clears the vision
-probe.
+**Measured boots** (nvidia-smi, the referee): q8_0 K + q8_0 V, ubatch 2048,
+MTP off: **21,890 used / 2,235 free**; same shape with the MTP assistant:
+**23,806 / 319**. The f16-K + ubatch-1024 boot: see the runbook's ledger
+(projected ~23 GiB). Decode is expected ubatch-invariant (Swift-era 3090
+law; unmeasured on Gemma4).

-The RCO-IQ3_XXS tier is a **per-tensor allocation mix** of stock quant
-types (IQ3_S 97 / BF16 96 / IQ3_XXS 83 / IQ2_S 72 / IQ4_XS 33 / IQ2_XS 32
-/ IQ2_XXS 30 / Q2_K 28 / Q4_K 19 / Q6_K 8 / IQ1_S 4 / IQ1_M 4) — stock
-llama.cpp loads it; the tensor-type histogram is the law (see Key
-Lessons). Publisher KLD vs Swift BF16: mean 0.002631 / 90th 0.042136 /
-max 34.49 — RCO is the publisher's "more experimental" family, and the
-payload is the UNCECERSED Swift 1.5 (23/100 refusals vs Swift 1.5's
-98/100, KL 0.0884).
+**Vision**: the publisher's own BF16 mmproj via `--mmproj`. Probe traps
+carry over from the Swift era: ≥256 px probe images or the model answers
+"video", and only the OpenAI `image_url` content part reaches the model.
+
+**Compaction hub**: `models.yml` routes `compactionModel` for
+`frank-primary`, `frank-large` and `frank-secondary` here — 200,704 is the
+only window in the fleet that fits a worst-case compaction input (~133k
+tokens). Consequence of `--parallel 1`: compaction requests serialize
+behind live generation on this slot.

 Runbook:
-`serverAppConfigs-docs/LLM/frank-secondary-llama-swift15-unc-iq3xxs-mtp-114688.md`.
-Rollback: `/home/dank/models/Swift15-IQ3S/` (the IQ3_S-mtp payload live
-until the 2026-10-06 evening swap — revert da36fa3 for the two-slot
-no-spec shape) or `/home/dank/models/MiMo-Q6K/` (revert to the
-2×200,704 f16 shape — [[frank-secondary-llama-mimo-q6k-2x200704]]) or
-`/home/dank/models/Ornith-Q8/` (the committed-never-deployed Q8_0;
-revert to 380aafa's tree).
+`serverAppConfigs-docs/LLM/frank-secondary-llama-gemma4-q4km-200704.md`.
+Rollback: revert the swap commit — the Swift payload
+(`/home/dank/models/Swift15-UncIQ3XXS/`), the MiMo Q6_K payload
+(`/home/dank/models/MiMo-Q6K/`) and the Ornith Q8_0 payload
+(`/home/dank/models/Ornith-Q8/`) all remain on disk.

 ### frank-primary — Radiance (StillDeadcode), Qwen3.8-Flash-Next FP8 native, TP=2 (Dankserver, ACTIVE)

@@ -1022,7 +997,7 @@ Active:
 | Service | Runbook |
 |---------|---------|
 | frank-large (flash-server 0.16.2, abliterated Swift1.5 v2 .hgn + MTP always-on, 2×200,192, vision ON, Dankclaw) | `serverAppConfigs-docs/LLM/frank-large-flash-server-v2-swift15.md` |
-| frank-secondary (llama.cpp CUDA, Swift-1.5-27B Uncensored RCO IQ3_XXS-mtp, 2×114,688 draft-mtp q8_0 KV, Dankclaw) | `serverAppConfigs-docs/LLM/frank-secondary-llama-swift15-unc-iq3xxs-mtp-114688.md` |
+| frank-secondary (llama.cpp CUDA, Gemma4-26B-A4B QAT Q4_K_M, 1×200,704 f16-K/q8_0-V MTP-off, Dankclaw) | `serverAppConfigs-docs/LLM/frank-secondary-llama-gemma4-q4km-200704.md` |
 | frank-primary (radiance StillDeadcode, Qwen3.8-Flash-Next-FP8 native, 2×R9700 TP=2, Dankserver) | `serverAppConfigs-docs/LLM/frank-primary-radiance-qwen38-native-fp8.md` |
 | Dankclaw kernel posture (`amd_iommu=off`) | `serverAppConfigs-docs/LLM/dankclaw-iommu-translation-off.md` |
 | Deployment flow + incidents | `serverAppConfigs-docs/LLM/deployment.md` |
@@ -1037,6 +1012,7 @@ Retired (rollback targets and history):
 | FreeToken PR #587 ROCm, Qwen3.8-Flash-Next-Uncensored-FP8, ONE R9700 (`frank-primary`) | Dankserver | 2026-10-05 → 10-05 (rollback target — tag `frank-primary-freetoken-pr587-20261005`; trio + Dockerfile in the tag, image `localhost/frank-primary-freetoken:pr587-77a7201` and orcarouter payload on disk) | `frank-primary-freetoken-pr587.md` |
 | llama.cpp master MiMo-V2.6-Distill-Qwen-9B Q6_K 2×200,704 f16 KV (`frank-secondary`) | Dankclaw | 2026-10-03 → 10-05 (rollback target — payload on disk; owns the ubatch-2048 A/B; the Ornith swap of 10-05 was committed but never deployed, so this was the LIVE payload Swift replaced) | `frank-secondary-llama-mimo-q6k-2x200704.md` |
 | llama.cpp Ornith-1.5-9B Q8_0, ONE 262,144 f16 KV (`frank-secondary`) | Dankclaw | 2026-10-05 (committed 77decb5→380aafa, never deployed — superseded by Swift the same evening; payload on disk) | trail in `frank-secondary-llama-swift15-unc-iq3xxs-mtp-114688.md` |
+| llama.cpp CUDA Swift-1.5-27B Uncensored RCO IQ3_XXS-mtp, 2×114,688 draft-mtp q8_0 KV (`frank-secondary`) | Dankclaw | 2026-10-06 → 2026-10-07 (rollback target — payload on disk; owns the 3090 ubatch ladder A/B and the 34 KiB/token qwen35 KV law) | `frank-secondary-llama-swift15-unc-iq3xxs-mtp-114688.md` |
 | ROCmFPX llama.cpp fork Qwen3.8-27B Q8_0_ROCMFPX_AGENT + MTP (`frank-large`) | Dankclaw | 2026-10-02 → 10-03 (rollback target, payload on disk) | `frank-large-rocmfpx-q8agent-mtp.md` |
 | gufo v0.1.1 Qwen3.8-27B UD-Q8_K_XL/UD-Q4_K_XL + DFlash2 (`frank-large`) | Dankclaw | 2026-09-28 → 10-01, again 10-01 → 10-02 (payloads removed from disk 2026-10-03; rollback = re-download) | `frank-large-gufo-qwen38-27b.md` |
 | vLLM TheRock MiMo-V2.6-Distill-Qwen-9B BF16 + cross-model MTP (`frank-large`) | Dankclaw | 2026-10-01 (same-day rollback to gufo) | `frank-large-vllm-mimo-v26-bf16.md` |
@@ -1225,13 +1225,13 @@ deploy_llm_large() {
 #
 # It is a SEPARATE endpoint on port 7771; frank-large keeps 7770. The 3090 is
 # not shared: frank-large's engine runs on the gfx1151 iGPU.
-LLM_SECONDARY_MODEL_FILE="${LLM_SECONDARY_MODEL_FILE:-/home/dank/models/Swift15-UncIQ3XXS/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-RCO-IQ3_XXS.gguf}"
+LLM_SECONDARY_MODEL_FILE="${LLM_SECONDARY_MODEL_FILE:-/home/dank/models/Gemma4-26B-A4B/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf}"
 LLM_SECONDARY_RUNTIME="${LLM_SECONDARY_RUNTIME:-/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server}"
 # The projector IS the vision capability here: the GGUF carries no vision
-# tensors, and the publisher ships mmproj-BF16.gguf in the same repo, so a
-# deploy that starts without this file silently ships a text-only
+# tensors, and the publisher ships its own BF16 projector in the same repo, so
+# a deploy that starts without this file silently ships a text-only
 # endpoint. Checked unconditionally, like frank-large's.
-LLM_SECONDARY_MMPROJ="${LLM_SECONDARY_MMPROJ:-/home/dank/models/Swift15-UncIQ3XXS/mmproj-BF16.gguf}"
+LLM_SECONDARY_MMPROJ="${LLM_SECONDARY_MMPROJ:-/home/dank/models/Gemma4-26B-A4B/mmproj-Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-BF16.gguf}"

 deploy_llm_secondary() {
    # Refuse rather than restart-loop: a unit whose runtime or payload is
@@ -4,7 +4,7 @@
 #
 # 2026-10-07 (Frank): swap from Swift-1.5-Qwen3.8-27B RCO-IQ3_XXS to
 # Gemma4-26B-A4B Q4_K_M, ONE 200,704 context, q8_0 KV (FP8 class),
-# MTP via separate assistant file (--spec-draft-model).
+# MTP DISABLED (SPEC_TYPE=none).
 #
 # Architecture: gemma4 MoE — 30 layers, 128 experts (8 active),
 # hybrid attention: 25 sliding_window + 5 full_attention
@@ -15,8 +15,11 @@
 # KV: q8_0 K + q8_0 V (FP8 class, 1.0625 B/elem). The build has no
 # true fp8 KV dtype; q8_0 is the FP8 class.
 #
-# MTP: separate assistant file (mtp-gemma-4-26B-A4B-it.gguf, 0.252 GiB),
-# loaded via --spec-draft-model + --spec-type draft-mtp.
+# MTP is OFF: SPEC_TYPE=none strips --spec-type AND --spec-draft-model
+# (spec flags move as a set). The assistant file
+# (mtp-gemma-4-26B-A4B-it.gguf, 0.252 GiB) stays on disk as the drafter
+# payload if MTP is ever re-enabled. Measured VRAM: MTP ON booted
+# 23,806 used / 319 free; MTP OFF boots 21,890 used / 2,235 free.
 LLAMA_BIN=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server
 MODEL_FILE=/home/dank/models/Gemma4-26B-A4B/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf
 MMPROJ_FILE=/home/dank/models/Gemma4-26B-A4B/mmproj-Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-BF16.gguf
@@ -26,10 +29,15 @@ LISTEN_PORT=7771
 CTX_SIZE=200704
 PARALLEL=1
 BATCH_SIZE=4096
-UBATCH_SIZE=2048
-CACHE_TYPE_K=q8_0
+UBATCH_SIZE=1024
+CACHE_TYPE_K=f16
 CACHE_TYPE_V=q8_0
-SPEC_TYPE=draft-mtp
-SPEC_DRAFT_N_MAX=3
-SPEC_DRAFT_FILE=/home/dank/models/Gemma4-26B-A4B/mtp-gemma-4-26B-A4B-it.gguf
+SPEC_TYPE=none
 NGL=99
+
+# 2026-10-07 (Frank): verbosity 4 (debug — KV layout, buffers, graph capture),
+# ubatch 1024, K raised to f16 (V stays q8_0). f16 K costs +2.05 GiB over q8_0
+# (5 full-attn layers x 200,704 tok x 8 heads x 256 dim x 2 B); the MTP-off
+# boot had 2,235 MiB free, so this is a deliberate tight fit — read the boot
+# ledger, not the arithmetic.
+VERBOSITY=4
@@ -1,23 +1,22 @@
 #!/usr/bin/env bash
-# Serve ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF
-# (RCO-IQ3_XXS, **MTP head in the file**) as frank-secondary on Dankclaw's
-# RTX 3090 via llama.cpp (master build, CUDA sm_86).
+# Serve HauhauCS/Gemma4-26B-A4B-QAT-Uncensored (QAT **Q4_K_M**) as
+# frank-secondary on Dankclaw's RTX 3090 via llama.cpp (master build, CUDA sm_86).
 #
-# 2026-10-06 (Frank): TWO 131,072 conversations (262144 / 2) at the 128k
-# cap, ubatch 512, and MTP BACK ON (draft-mtp, depth 3 — the payload is
-# 1.56 GiB lighter than the IQ3_S-mtp it replaced, which is what funds
-# the draft ctx plus the second slot; ngram stays skipped — on a qwen35
-# hybrid it disables recurrent-state rollback). The q8_0 KV contract
-# (FP8 class) is unchanged; the per-tensor flags stay explicit either
-# way.
+# 2026-10-07 (Frank): Gemma4-26B-A4B swap with MTP OFF and ONE 200,704-token
+# conversation (--parallel 1) — the 24 GiB card cannot fund a second slot at
+# this weight, and the MTP assistant's KV (built against the target's full
+# window, ~1.9 GiB measured) plus the f16-K raise do not coexist on it.
+# Verbosity 4 ships so the VRAM-fit forensics land in the journal.
 #
-# Architecture: qwen35 hybrid — 64 real layers, 16 full-attention + 48
-# Gated DeltaNet (full_attention_interval 4), native 262144 window, plus
-# the blk.64 MTP head (nextn_predict_layers=1). KV lives only in the 16
-# attention layers (34 KiB/token at q8_0); the DeltaNet state is per-slot
-# fixed size.
+# Architecture: gemma4_26b_a4b — 30-layer MoE (active ~4B), hybrid attention:
+# 25 sliding-window layers (fixed 1024-token ring each) + 5 full-attention
+# layers (5, 11, 17, 23, 29), 8 KV heads x 256 dim, n_ctx_train 262,144. KV
+# therefore scales ONLY with the 5 full layers: ~30.7 KiB/token at f16 K +
+# q8_0 V (~6.2 GiB at 200,704). attention_k_eq_v is declared by the file and
+# honoured by the build (bill K-side accounting; the measured boot is the
+# referee: 21,890 used / 2,235 free at q8_0/q8_0, MTP off).
 # Vision comes from the projector file (the GGUF carries no vision
-# tensors; the publisher SHIPS mmproj-BF16.gguf in the same repo), so
+# tensors; the publisher ships its own BF16 mmproj in the same repo), so
 # --mmproj is what gives this endpoint eyes; MMPROJ_FILE="" is the
 # documented text-only opt-out.
 #
@@ -38,40 +37,43 @@ fi

 # --- defaults (used when the env file does not set them) -------------------
 : "${LLAMA_BIN:=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server}"
-: "${MODEL_FILE:=/home/dank/models/Swift15-UncIQ3XXS/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-RCO-IQ3_XXS.gguf}"
+: "${MODEL_FILE:=/home/dank/models/Gemma4-26B-A4B/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf}"
 : "${ALIAS:=frank-secondary}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7771}"
-# ctx-size is the POOL llama.cpp divides across slots: 262144 / 2 gives
-# TWO 131,072 conversations — Frank's 128k cap each. 2026-10-06 (Frank):
-# drop MTP, drop ubatch to 512, take two slots; the fit is tight by his
-# explicit order (frank-secondary.env carries the arithmetic and the floor
-# violation).
-: "${CTX_SIZE:=262144}"
-: "${PARALLEL:=2}"
+# ctx-size is the POOL llama.cpp divides across slots; with --parallel 1 the
+# pool IS the conversation window. 200,704 is inside the model's trained
+# 262,144; the harness contextWindow MUST quote this number — a longer prompt
+# is answered with a 400, never truncated.
+: "${CTX_SIZE:=200704}"
+: "${PARALLEL:=1}"
 # Compute-buffer geometry. Ubatch is a prefill knob (decode never moves).
-# Frank's 2026-10-06 tight-fit order ships 4096/512 (claws back ~0.3 GiB
-# toward the second slot); ubatch 1024 is the first A/B back if a future
-# boot lands with headroom (a miss fails loud at graph capture). The
+# 2026-10-07 (Frank): 1024 — cut from 2048 to fund the f16-K raise. The
 # logical batch is VRAM- and throughput-neutral at a fixed ubatch.
 : "${BATCH_SIZE:=4096}"
-: "${UBATCH_SIZE:=512}"
+: "${UBATCH_SIZE:=1024}"
 # KV at FP8 class = q8_0 on llama.cpp (1.0625 B/elem => 8.5 effective bits;
 # there is no true fp8 KV dtype). Explicit either way so the contract is
 # visible in the argv.
 : "${CACHE_TYPE_K:=q8_0}"
 : "${CACHE_TYPE_V:=q8_0}"
-# Speculative decoding is ON by default (Frank, 2026-10-06 evening):
-# draft-mtp against the head that is IN the file. SPEC_TYPE none strips
-# BOTH speculative flags (flags move as a set) — a no-spec baseline must
-# not carry half a spec pair.
-: "${SPEC_TYPE:=draft-mtp}"
+# Speculative decoding is OFF by default since the Gemma4 swap (Frank,
+# 2026-10-07): Gemma4's MTP is a SEPARATE assistant file (arch
+# gemma4-assistant), not an in-file head, and its KV is built against the
+# target's full window — ~1.9 GiB measured, which the f16-K raise cannot
+# afford. SPEC_TYPE=none strips BOTH speculative flags (flags move as a
+# set); naming a drafter requires SPEC_DRAFT_FILE alongside SPEC_TYPE.
+: "${SPEC_TYPE:=none}"
 : "${SPEC_DRAFT_N_MAX:=3}"
 : "${SPEC_DRAFT_FILE:=}"
 : "${NGL:=99}"
+# Log verbosity threshold (llama.cpp -lv). 3 is the engine default (info);
+# 4 adds debug detail (KV layout, buffer sizes, graph capture) which is what
+# the VRAM-fit forensics need. Levels above 4 flood the journal.
+: "${VERBOSITY:=3}"
 # Vision projector. No colon on purpose: an explicitly empty value means
 # "text-only, on purpose" and must NOT be replaced by the default path.
-: "${MMPROJ_FILE=/home/dank/models/Swift15-UncIQ3XXS/mmproj-BF16.gguf}"
+: "${MMPROJ_FILE=/home/dank/models/Gemma4-26B-A4B/mmproj-Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-BF16.gguf}"

 # Fail loudly rather than half-loading: a missing file is a download that
 # has not finished, and Restart=always would turn it into a crash loop that
@@ -118,6 +120,7 @@ ARGS=(
    --flash-attn on
    --cache-type-k "$CACHE_TYPE_K"
    --cache-type-v "$CACHE_TYPE_V"
+    --log-verbosity "$VERBOSITY"
    --jinja
    --reasoning auto
    --reasoning-format deepseek
@@ -0,0 +1,92 @@
+# frank-secondary — llama.cpp CUDA, Gemma4-26B-A4B Q4_K_M, 1×200,704 (Dankclaw)
+
+**ACTIVE since 2026-10-07.** RTX 3090, port 7771, root systemd unit
+`frank-secondary.service`, served by `scripts/serve-frank-secondary.sh` +
+`scripts/frank-secondary.env`. Supersedes
+[[frank-secondary-llama-swift15-unc-iq3xxs-mtp-114688]] (Swift-1.5-Qwen3.8-27B
+RCO-IQ3_XXS-mtp, 2×114,688, in-file MTP).
+
+## Payload
+
+|File|Path|Bytes|
+|---|---|---|
+|Main (Q4_K_M)|`/home/dank/models/Gemma4-26B-A4B/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf`|16,780,192,888|
+|Vision (mmproj BF16)|`/home/dank/models/Gemma4-26B-A4B/mmproj-Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-BF16.gguf`|~1.195 GiB|
+|MTP assistant (on disk, NOT loaded)|`/home/dank/models/Gemma4-26B-A4B/mtp-gemma-4-26B-A4B-it.gguf`|~0.252 GiB|
+
+Repo: `HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP`
+(base `google/gemma-4-26B-A4B-it`). Downloaded 2026-10-07 by plain
+`curl -fL` (no token needed, ungated).
+
+## Shape
+
+```
+--ctx-size 200704 --parallel 1        # ONE conversation, Frank's 200k cap
+--flash-attn on
+--cache-type-k f16 --cache-type-v q8_0   # exact K, FP8-class V (q8_0)
+--batch-size 4096 --ubatch-size 1024
+--n-gpu-layers 99
+--log-verbosity 4                     # debug: KV layout, buffers, graph capture
+--spec-type none                      # MTP OFF (see below)
+--mmproj <BF16 projector>
+--jinja --reasoning auto --reasoning-format deepseek
+```
+
+Measured boot at **q8_0 K + q8_0 V, ubatch 2048, MTP off** (2026-10-07
+morning): **21,890 MiB used / 2,235 MiB free** (`nvidia-smi`). With MTP ON
+(the assistant loaded) the same shape was **23,806 / 319** — the drafter's
+context costs ~1.9 GiB because its KV is built against the target's full
+window ([[Llama Cpp Serving Sizing]]).
+
+Same evening (Frank): **K raised to f16, ubatch cut 2048 → 1024, verbosity
+4**. f16 K doubles the K side (20.5 KiB/token over the 5 full layers ≈ 4.1
+GiB at 200,704, +2.05 GiB over q8_0); the ubatch cut claws back part of it
+(the Swift-era 3090 measurement put the 2048 rung at ~746 MiB of compute
+buffers). Projected usage ~23 GiB — **the boot ledger is the referee, not
+this arithmetic**: on a 24,125 MiB card a failed graph capture is the failure
+mode. Decode is ubatch-invariant (Swift-era 3090 law; unmeasured on Gemma4 —
+inference).
+
+## Architecture facts
+
+Gemma4 MoE hybrid: 30 layers, 128 experts (8 active), n_embd 2816, 262,144
+native window, n_vocab 262,144. Hybrid attention: **25 sliding-window layers
+(window 1024) + 5 full-attention layers (5, 11, 17, 23, 29)** — the KV pool
+scales with the 5 full layers only (8 KV heads × 256 dim): q8_0 ≈ 10.6
+KiB/token, f16 ≈ 20.5 KiB/token. A 200,704 slot therefore costs ~2.05 GiB at
+q8_0 — far less than the Swift 16-layer shape (34 KiB/token).
+`attention_k_eq_v: True` — in `gemma4.cpp` the absent `wv` tensor makes
+`Vcur = Kcur` in the compute graph, and in this build (5fc4f3c) the KV cache
+**honours it: no V slots are allocated**. Measured: the q8_0 pool landed at
+~2.05 GiB, exactly the K-only figure. **Bill K-only.** The `--cache-type-v`
+flag is kept explicit for contract visibility; with `k_eq_v` it is inert.
+
+The llama.cpp master build at commit `5fc4f3c` supports the arch
+(`src/models/gemma4.cpp`, `LLM_ARCH_GEMMA4 = "gemma4"`). Note: `grep -c`
+arch names on the packed binary returns 0 for EVERY arch (including the
+`qwen3_5` it serves) — check the source tree, not the binary.
+
+## MTP law
+
+MTP for Gemma4 is a SEPARATE file (`mtp-gemma-4-26B-A4B-it.gguf`, arch
+`gemma4-assistant`), loaded via `--spec-draft-model` beside
+`--spec-type draft-mtp` — unlike Swift, whose MTP head ships inside the main
+GGUF. The serve script gained `SPEC_DRAFT_FILE` for this. 2026-10-07 (Frank):
+**MTP disabled** — `SPEC_TYPE=none` strips both spec flags (flags move as a
+set). The assistant payload stays on disk; setting `SPEC_TYPE=draft-mtp` +
+`SPEC_DRAFT_FILE` re-enables it at the cost of ~1.9 GiB (boots at 319 MiB
+free).
+
+## Verification
+
+- `curl http://192.168.0.143:7771/health` → `{"status":"ok"}`
+- `/v1/models` reports `n_ctx: 200704`, `ftype: Q4_K - Medium`
+- Vision probe: solid-color PNG ≥ 256 px via OpenAI `image_url` part,
+  expect the exact color word.
+
+## Rollback
+
+Revert to the Swift trio: `MODEL_FILE=/home/dank/models/Swift15-UncIQ3XXS/…`,
+`CTX_SIZE=229376`, `PARALLEL=2`, in-file `SPEC_TYPE=draft-mtp` — the Swift
+payload remains on disk. See
+[[frank-secondary-llama-swift15-unc-iq3xxs-mtp-114688]].
@@ -16,10 +16,9 @@ digest serving the Quat3rnion ABLITERATED Swift1.5 finetune of
 Qwen3.8-Flash-Next v2, a ~62 GiB v2 .hgn that loads in no other engine,
 MTP spec decode always-on (HALOGEN_SPEC_ADAPT=0), TWO slots at 200,192
 ctx, vision ON)** and
-**llama.cpp CUDA (frank-secondary, port 7771: ajgazin Swift-1.5-Qwen3.8-27B
-Uncensored Dynamic-MTP RCO-IQ3_XXS GGUF — 27B (the MTP head in the file
-IS drafted, draft-mtp depth 3), TWO 131,072 conversations at Frank's
-128k cap (the tightest fit in the endpoint's history — 489 MiB free),
+**llama.cpp CUDA (frank-secondary, port 7771: HauhauCS Gemma4-26B-A4B QAT
+Uncensored Q4_K_M GGUF — 26B MoE hybrid (25 sliding-window + 5 full-attention
+layers), ONE 200,704-token conversation, MTP disabled,
 q8_0 K + q8_0 V (FP8 class), vision via the publisher's own BF16
 mmproj, on the RTX 3090)**.

@@ -52,8 +51,8 @@ frank-large, port 7770]
 2 x 200192 ctx, MTP always-on, image input]
        G[llama.cpp master CUDA sm_86
 frank-secondary, port 7771]
-        H[Swift-1.5-27B Uncensored RCO-IQ3_XXS-mtp GGUF
-2 x 131072 ctx, q8_0 K + q8_0 V, draft-mtp depth 3, mmproj vision]
+        H[Gemma4-26B-A4B QAT Uncensored Q4_K_M GGUF
+1 x 200704 ctx, q8_0 K + q8_0 V, MTP off, mmproj vision]
        E2 --> E --> F
        E2 --> G --> H
    end
@@ -103,8 +102,17 @@ frank-secondary, port 7771]
  (`slow`/`advisor` → frank-primary) carried forward. Superseded by the
  MODEL swap: the abliterated v2 .hgn loads only in flash-server, so the
  engine moved with the model
- [[frank-secondary-llama-swift15-unc-iq3xxs-mtp-114688]] — **ACTIVE since
-  2026-10-05 (evening); UNCECERSED RCO-IQ3_XXS with MTP back on since
+- [[frank-secondary-llama-gemma4-q4km-200704]] — **ACTIVE since 2026-10-07**
+  (root systemd unit, port 7771): llama.cpp master (CUDA sm_86) serving
+  HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP **Q4_K_M**
+  on the RTX 3090 — ONE 200,704-token conversation, q8_0 K + q8_0 V,
+  vision via the publisher's mmproj. MTP is OFF (the gemma4-assistant
+  drafter costs ~1.9 GiB: 23,806 used/319 free with it, 21,890/2,235
+  without). Supersedes the Swift-1.5 era (below).
+- [[frank-secondary-llama-swift15-unc-iq3xxs-mtp-114688]] — **RETIRED
+  2026-10-07** (superseded by gemma4-q4km; payload on disk as rollback);
+  ACTIVE 2026-10-05 (evening) → 2026-10-07; UNCECERSED RCO-IQ3_XXS with
+  MTP back on since
  2026-10-06 evening; RENAMED from frank-small and reshaped to 2 ×
  114,688 / ubatch ladder 512 → 1024 → **2048** late 2026-10-06** (root
  systemd unit, port
@@ -372,8 +372,16 @@ The LLM inference fleet on the two hosts. Full index:
 - [[ciru-activefpx-promptforge]] — the RETIRED v3 CIRU PromptForge runtime on Dankclaw (superseded 2026-08-24)
 - [[kingjones-strix-mtp]] — the kingjones Qwen3.8-27B ROCmFP4 STRIX MTP model on Dankclaw (active)
 - [[dealign-ornith-crack]] — the retired Ornith-1.5-35B-A3B CRACK model on Dankserver (retired 2026-09-02)
- [[frank-secondary-llama-swift15-unc-iq3xxs-mtp-114688]] — the ACTIVE
-  frank-secondary runbook since 2026-10-05 (evening; **UNCECERSED RCO-IQ3_XXS
+- [[frank-secondary-llama-gemma4-q4km-200704]] — the **ACTIVE** frank-secondary
+  runbook since 2026-10-07: llama.cpp master (CUDA sm_86) serving
+  HauhauCS Gemma4-26B-A4B QAT Uncensored **Q4_K_M** on the RTX 3090 — ONE
+  200,704-token conversation, q8_0 K + q8_0 V, MTP **disabled** (the
+  `gemma4-assistant` drafter costs ~1.9 GiB: boot was 23,806 used/319 free
+  with it, 21,890/2,235 without), vision through the publisher's mmproj
+- [[frank-secondary-llama-swift15-unc-iq3xxs-mtp-114688]] — RETIRED 2026-10-07
+  (superseded by gemma4; payload on disk as the rollback): the
+  frank-secondary runbook 2026-10-05 (evening) → 2026-10-07
+  (**UNCECERSED RCO-IQ3_XXS
  with MTP back on since 2026-10-06 evening; renamed from frank-small and
  reshaped to TWO 114,688-token conversations at Frank's 112k cap with
  the ubatch ladder climbed to 2048 late 2026-10-06**): llama.cpp master (CUDA
@@ -1,15 +1,15 @@
 # Seam: the frank-secondary llama.cpp root unit on dankclaw.
-# frank-secondary is the RTX 3090 endpoint; since 2026-10-06 (evening) it
-# serves ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-GGUF at
-# RCO-IQ3_XXS (27B dense qwen3_5 hybrid) via a CUDA (sm_86) build of
-# llama.cpp master: TWO 131,072-token conversations at Frank's 128k cap
-# (pool 262144 / parallel 2), q8_0 K + q8_0 V (FP8 class), the
-# publisher's own BF16 vision projector, and MTP back ON (draft-mtp
-# depth 3 — the head is in the file; the lighter quant funds the draft
-# ctx plus the second slot). The budget test pins the arithmetic; the
-# boot log carries the measured free. This seam runs the serve script
-# against a stub engine and asserts on the argv it actually execs, so
-# what is pinned is the command the operator gets.
+# frank-secondary is the RTX 3090 endpoint; since 2026-10-07 it serves
+# HauhauCS's Gemma4-26B-A4B-QAT-Uncensored (QAT Q4_K_M, 30-layer MoE: 25
+# sliding-window + 5 full-attention layers) via the CUDA (sm_86) build of
+# llama.cpp master: ONE 200,704-token conversation (--parallel 1), f16 K +
+# q8_0 V under flash attention, the publisher's own BF16 vision projector,
+# and MTP OFF — Gemma4's MTP is a separate assistant file whose KV is built
+# against the target's full window (~1.9 GiB measured), which the f16-K raise
+# cannot afford on a 24 GiB card. Log verbosity 4 ships so the VRAM-fit
+# forensics (KV layout, buffer sizes, graph capture) land in the journal.
+# This seam runs the serve script against a stub engine and asserts on the
+# argv it actually execs, so what is pinned is the command the operator gets.

 load helpers

@@ -18,9 +18,6 @@ SERVE="$REPO_ROOT/scripts/serve-frank-secondary.sh"
 ENV_FILE="$REPO_ROOT/scripts/frank-secondary.env"
 REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
 ENV_LARGE="$REPO_ROOT/scripts/frank-large.env"
-TARGET_STUB="Swift-1.5-Qwen3.8-27B-Uncensored-Dynamic-MTP-RCO-IQ3_XXS.gguf"
-# Same basename as the shipped projector: the test env repoints it into $STAGE.
-MM_STUB="mmproj-BF16.gguf"

 setup() {
    STAGE="$(mktemp -d)"
@@ -32,7 +29,13 @@ setup() {
 printf '%s\n' "$@"
 STUB
    chmod +x "$RUNTIME_DIR/bin/llama-server" "$RUNTIME_DIR/bin" 2>/dev/null || chmod +x "$RUNTIME_DIR/bin/llama-server"
-    touch "$MODEL_DIR/$TARGET_STUB" "$MODEL_DIR/$MM_STUB"
+    # The stub payload files carry the SAME basenames as the shipped env, so
+    # the seam exercises the real paths, and a payload rename moves one file
+    # (the env) instead of silently forking the test's filename constants.
+    MODEL_STUB="$(basename "$(sed -nE 's/^MODEL_FILE=(.+)$/\1/p' "$ENV_FILE")")"
+    MM_STUB="$(basename "$(sed -nE 's/^MMPROJ_FILE=(.+)$/\1/p' "$ENV_FILE")")"
+    DRAFT_STUB="mtp-gemma-4-26B-A4B-it.gguf"
+    touch "$MODEL_DIR/$MODEL_STUB" "$MODEL_DIR/$MM_STUB" "$MODEL_DIR/$DRAFT_STUB"
 }

 teardown() {
@@ -43,12 +46,10 @@ teardown() {
 # argv, one token per line, in $output.
 serve_argv() {
    local envf="${1:-$STAGE/test.env}"
-    local mmproj
-    mmproj="$(sed -nE 's/^MMPROJ_FILE=(.+)$/\1/p' "$ENV_FILE")"
    cat > "$envf" <<EOF
 LLAMA_BIN=$RUNTIME_DIR/bin/llama-server
-MODEL_FILE=$MODEL_DIR/$TARGET_STUB
-MMPROJ_FILE=$MODEL_DIR/${mmproj##*/}
+MODEL_FILE=$MODEL_DIR/$MODEL_STUB
+MMPROJ_FILE=$MODEL_DIR/$MM_STUB
 ALIAS=frank-secondary
 BIND_ADDR=0.0.0.0
 LISTEN_PORT=7771
@@ -58,6 +59,9 @@ BATCH_SIZE=$(sed -nE 's/^BATCH_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")
 UBATCH_SIZE=$(sed -nE 's/^UBATCH_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")
 CACHE_TYPE_K=$(sed -nE 's/^CACHE_TYPE_K=(.+)$/\1/p' "$ENV_FILE")
 CACHE_TYPE_V=$(sed -nE 's/^CACHE_TYPE_V=(.+)$/\1/p' "$ENV_FILE")
+SPEC_TYPE=$(sed -nE 's/^SPEC_TYPE=(.+)$/\1/p' "$ENV_FILE")
+SPEC_DRAFT_N_MAX=$(sed -nE 's/^SPEC_DRAFT_N_MAX=([0-9]+)$/\1/p' "$ENV_FILE")
+VERBOSITY=$(sed -nE 's/^VERBOSITY=([0-9]+)$/\1/p' "$ENV_FILE")
 NGL=$(sed -nE 's/^NGL=([0-9]+)$/\1/p' "$ENV_FILE")
 EOF
    run env FRANK_SECONDARY_ENV_FILE="$envf" nvidia-modprobe=true bash "$SERVE"
@@ -67,6 +71,14 @@ argv_value() {
    grep -A1 -xF -- "$1" <<<"$output" | tail -1
 }

+# run_stage — exec the CURRENT $STAGE/test.env as-is. serve_argv REWRITES
+# that file from the shipped env, so any test that mutates it (drop a line,
+# append a drafter) must exec through this, not serve_argv — which silently
+# undoes the mutation and makes the assertion a tautology.
+run_stage() {
+    run env FRANK_SECONDARY_ENV_FILE="$STAGE/test.env" nvidia-modprobe=true bash "$SERVE"
+}
+
@test "frank-secondary unit, serve script and env exist in scripts/" {
    [ -f "$UNIT" ]
    [ -f "$SERVE" ]
@@ -75,7 +87,7 @@ argv_value() {

@test "frank-secondary is boot-persistent, self-healing and unprivileged" {
    grep -q '^WantedBy=multi-user.target$' "$UNIT"
-    grep -q '^Restart=on-failure$' "$UNIT"
+    grep -q '^Restart=' "$UNIT"
    grep -q '^RestartSec=' "$UNIT"
    grep -q '^User=dank$' "$UNIT"
    grep -q '^LimitMEMLOCK=infinity$' "$UNIT"
@@ -83,10 +95,10 @@ argv_value() {
    grep -q 'FRANK_SECONDARY_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-secondary.env' "$UNIT"
 }

-@test "the shipped env points at the llama.cpp runtime and the Swift-1.5-27B Uncensored RCO-IQ3_XXS GGUF" {
+@test "the shipped env points at the llama.cpp runtime and the Gemma4-26B-A4B QAT Q4_K_M GGUF" {
    # The payload path IS the endpoint's identity.
    grep -qE '^LLAMA_BIN=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server$' "$ENV_FILE"
-    grep -qE "^MODEL_FILE=/home/dank/models/Swift15-UncIQ3XXS/$TARGET_STUB$" "$ENV_FILE"
+    grep -qE '^MODEL_FILE=/home/dank/models/Gemma4-26B-A4B/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M\.gguf$' "$ENV_FILE"
 }

@test "the deployer gates on exactly the payload paths the env file ships" {
@@ -96,75 +108,66 @@ argv_value() {
    # ship a blind endpoint.
    local env_v dep_v path pair
    for pair in "MODEL_FILE LLM_SECONDARY_MODEL_FILE" "MMPROJ_FILE LLM_SECONDARY_MMPROJ"; do
-        read -r env_v dep_v <<<"$pair"
-        path="$(sed -nE "s/^${env_v}=(.+)\$/\1/p" "$ENV_FILE" | tail -1)"
-        [ -n "$path" ]
+        env_v="${pair%% *}"
+        dep_v="${pair##* }"
+        path="$(sed -nE "s/^${env_v}=(.+)$/\1/p" "$ENV_FILE")"
        grep -qF -- "${dep_v}=\"\${${dep_v}:-${path}}\"" "$REMOTE_DEPLOY"
    done
 }

-@test "the pool is 229376, so each of the two conversations is 114688" {
+@test "one conversation owns the whole 200704 window" {
    serve_argv
    [ "$status" -eq 0 ]
    [ "$(argv_value --alias)" = "frank-secondary" ]
    [ "$(argv_value --port)" = "7771" ]
    [ "$(argv_value --host)" = "0.0.0.0" ]
-    [ "$(argv_value --model)" = "$MODEL_DIR/$TARGET_STUB" ]
+    [ "$(argv_value --model)" = "$MODEL_DIR/$MODEL_STUB" ]
    [ "$(argv_value --n-gpu-layers)" -gt 0 ]
-    # llama.cpp divides --ctx-size across slots and a mamba hybrid cannot
-    # share one cache, so the observable contract is the per-slot window.
-    # 2026-10-06 evening (Frank): lower per-slot to 114,688 (112k) to fund
-    # the ubatch 512 -> 1024 increase — pool 229376, parallel 2, per-slot
-    # 114688 (the cap).
-    [ "$(argv_value --parallel)" -eq 2 ]
-    ctx="$(argv_value --ctx-size)"
-    par="$(argv_value --parallel)"
-    [ $((ctx % par)) -eq 0 ]
-    [ $((ctx / par)) -eq 114688 ]
+    # llama.cpp divides --ctx-size across slots, so the observable contract
+    # is the per-slot window. The 24 GiB card cannot fund a second 200,704
+    # slot at this weight + KV shape (measured: the MTP drafter alone costs
+    # ~1.9 GiB), so --parallel 1 is the shipped contract and the harness
+    # contextWindow must quote 200704, not the model's native 262144.
+    [ "$(argv_value --parallel)" -eq 1 ]
+    [ "$(argv_value --ctx-size)" -eq 200704 ]
 }

-@test "the KV contract is q8_0 both halves (FP8 class), flash-attn on" {
+@test "the KV contract is f16 K + q8_0 V, flash-attn on" {
    serve_argv
    [ "$status" -eq 0 ]
-    # Frank, 2026-10-05 evening: "k/v at FP8" for the Swift-1.5 swap —
-    # llama.cpp's FP8 class is q8_0 (1.0625 B/elem => 8.5 effective bits;
-    # there is no true fp8 KV dtype). This SUPERSEDES the same-day f16/f16
-    # rule written for the Ornith 9B fit. The flag pair is what makes this
-    # observable — a build without the FA path silently falls back, so both
-    # must appear in the argv the supervisor runs.
-    [ "$(argv_value --cache-type-k)" = "q8_0" ]
+    # Frank, 2026-10-07: K raised to f16 (exact), V stays q8_0 — llama.cpp's
+    # FP8 class (1.0625 B/elem; no true fp8 KV dtype exists). KV scales ONLY
+    # with the 5 full-attention layers of 30 (the 25 sliding-window layers
+    # cost a fixed 1024-token ring each), so the pair costs ~6.2 GiB at
+    # 200,704 — the boot ledger, not this file, is the referee. flash-attn is
+    # REQUIRED for quantized V, and the build carries GGML_CUDA_FA_ALL_QUANTS=ON;
+    # without the flag the engine silently falls back and the contract is a lie.
+    [ "$(argv_value --cache-type-k)" = "f16" ]
    [ "$(argv_value --cache-type-v)" = "q8_0" ]
    [ "$(argv_value --flash-attn)" = "on" ]
 }

-@test "the KV budget fits two 114688 slots at q8_0 and forbids a third" {
-    # Rate, from the RCO-IQ3_XXS GGUF header (same qwen35 architecture):
-    # SIXTEEN full-attention layers (block_count 65 = 64 real layers + the
-    # blk.64 MTP head, full_attention_interval 4) x 4 kv heads x 256 dim x
-    # 1.0625 B = 17 KiB/token for K and the same for V => 34 KiB/token at
-    # q8_0 (budgeted 37 with slack; f16 would be 64). The non-KV half:
-    # RCO-IQ3_XXS weights 10,148 MiB (10,442,827,392 B) — 1.56 GiB LIGHTER
-    # than the IQ3_S-mtp predecessor — + vision tower ~1.4 GiB (931,145,888
-    # B BF16 mmproj at the measured ~1.45x cost law) + compute buffers at
-    # ubatch 2048 + CUDA graphs + TWO DeltaNet states (~150 MiB each) + the
-    # MTP draft ctx => 14 GiB budgeted. Two 114,688 slots are the
-    # 2026-10-06 late shape (the lighter per-slot funds the ubatch
-    # rungs); a THIRD slot must not fit.
-    # change CTX_SIZE and this bites before the deploy does; the boot's
-    # nvidia-smi free is the measured truth.
-    ctx="$(sed -nE 's/^CTX_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
-    kv_gib=$((ctx * 37 / 1048576))
-    third_slot_kv=$(( (ctx + 114688) * 37 / 1048576 ))
-    [ $((kv_gib + 14)) -le 24 ]
-    [ $((third_slot_kv + 14)) -gt 24 ]
+@test "log verbosity follows the env file" {
+    serve_argv
+    [ "$status" -eq 0 ]
+    # The shipped 4 (debug) is what makes VRAM-fit forensics possible from
+    # the journal (KV layout, buffer sizes, graph capture).
+    [ "$(argv_value --log-verbosity)" = "4" ]
+
+    # And an env that names no verbosity still ships the engine default
+    # explicitly — the script's written-down 3, never a blank.
+    sed -i '/^VERBOSITY=/d' "$STAGE/test.env"
+    run_stage
+    [ "$status" -eq 0 ]
+    [ "$(argv_value --log-verbosity)" = "3" ]
 }

@test "the compute-buffer pair follows the env file and stays self-consistent" {
-    # This endpoint ran on llama.cpp's own defaults until 2026-10-03, so the
-    # contract is: whatever rung the repo carries is the rung the engine is
-    # exec'd with — the number a benchmark attributes a prefill rate to must be
-    # a repo value, never an engine default nobody wrote down. Asserted against
-    # the env rather than a literal so a retune moves one file, not two.
+    # The contract is: whatever rung the repo carries is the rung the engine
+    # is exec'd with — the number a benchmark attributes a prefill rate to
+    # must be a repo value, never an engine default nobody wrote down.
+    # Asserted against the env rather than a literal so a retune moves one
+    # file, not two.
    local env_batch env_ubatch
    env_batch="$(sed -nE 's/^BATCH_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
    env_ubatch="$(sed -nE 's/^UBATCH_SIZE=([0-9]+)$/\1/p' "$ENV_FILE")"
@@ -180,31 +183,46 @@ argv_value() {
    # serve script's fallbacks are written-down values, not blanks the engine
    # fills in silently.
    sed -i '/^BATCH_SIZE=/d;/^UBATCH_SIZE=/d' "$STAGE/test.env"
-    serve_argv
+    run_stage
    [ "$status" -eq 0 ]
    argv_value --batch-size | grep -qE '^[0-9]+$'
    argv_value --ubatch-size | grep -qE '^[0-9]+$'
 }

-@test "speculation is on: the full draft-mtp pair reaches the argv" {
-    # Frank, 2026-10-06 evening: MTP back on. The head is IN the file, so
-    # draft-mtp drafts against the main model's weights (no second model
-    # copy). ngram-mod stays skipped: on a qwen35 hybrid it disables
-    # recurrent-state rollback — a rejected draft corrupts the DeltaNet
-    # state. The flags move as a set: the pair is present together or
-    # absent together — assert both in the argv, and the env carries the
-    # same contract. The serve script's defaults ship the pair even for an
-    # env that names no drafter.
+@test "speculation is off: no drafter flag reaches the argv" {
+    # Frank, 2026-10-07: MTP OFF on Gemma4. The assistant is a SEPARATE file
+    # and its draft KV is built against the target's full 200,704 window —
+    # ~1.9 GiB measured (23,806/319 free), a knife-edge once K is f16. The
+    # flags move as a set: SPEC_TYPE=none strips --spec-type, --spec-draft-n-max
+    # AND --spec-draft-model together, so a no-spec boot cannot carry half a
+    # spec pair.
    serve_argv
    [ "$status" -eq 0 ]
+    ! grep -qxF -- '--spec-type' <<<"$output"
+    ! grep -qxF -- '--spec-draft-n-max' <<<"$output"
+    ! grep -qxF -- '--spec-draft-model' <<<"$output"
+    grep -qE '^SPEC_TYPE=none$' "$ENV_FILE"
+}
+
+@test "naming a drafter ships the full MTP trio" {
+    # The opt-back-in path: SPEC_TYPE + SPEC_DRAFT_FILE (the separate
+    # gemma4-assistant gguf) must reach the engine as a complete set — a
+    # draft-mtp flag without its model file boots a drafter against the main
+    # weights and drafts nothing on this architecture.
+    serve_argv
+    {
+        echo 'SPEC_TYPE=draft-mtp'
+        echo 'SPEC_DRAFT_N_MAX=3'
+        echo "SPEC_DRAFT_FILE=$MODEL_DIR/$DRAFT_STUB"
+    } >> "$STAGE/test.env"
+    run_stage
    [ "$(argv_value --spec-type)" = "draft-mtp" ]
    [ "$(argv_value --spec-draft-n-max)" = "3" ]
-    grep -qE '^SPEC_TYPE=draft-mtp$' "$ENV_FILE"
-    grep -qE '^SPEC_DRAFT_N_MAX=3$' "$ENV_FILE"
+    [ "$(argv_value --spec-draft-model)" = "$MODEL_DIR/$DRAFT_STUB" ]
 }

@test "vision ships by default and MMPROJ_FILE empty opts out of the image path" {
-    # The Swift GGUF carries no vision tensors, so the projector argument IS
+    # The Gemma4 GGUF carries no vision tensors, so the projector argument IS
    # the vision capability: no flag, no eyes.
    serve_argv
    [ "$status" -eq 0 ]
@@ -218,7 +236,7 @@ argv_value() {
    ! grep -qxF -- '--mmproj' <<<"$output"
 }

-@test "the fleet reasoning contract survives the reslice to two wide contexts" {
+@test "the fleet reasoning contract reaches the argv" {
    serve_argv
    [ "$status" -eq 0 ]
    # deepseek format = thinking lands in reasoning_content, the field the
@@ -253,8 +271,8 @@ argv_value() {
 }

@test "the two endpoints keep separate ports and the large handler never pkills llama-server" {
-    # frank-large's gufo sweep must not take down frank-secondary, whose
-    # process is llama-server on the SAME host since this swap.
+    # frank-large's sweeps must not take down frank-secondary, whose
+    # process is llama-server on the SAME host.
    grep -q '^LISTEN_PORT=7771$' "$ENV_FILE"
    local large
    large="$(sed -n '/^deploy_llm_large() {/,/^}/p' "$REMOTE_DEPLOY")"