diff --git a/scripts/deploy-remote.sh b/scripts/deploy-remote.sh
index 72c2fa8..91edada 100755
--- a/scripts/deploy-remote.sh
+++ b/scripts/deploy-remote.sh
@@ -1198,12 +1198,12 @@ 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_SMALL_MODEL_FILE="${LLM_SMALL_MODEL_FILE:-/home/dank/models/MiMo-Q5KM/MiMo-V2.6-Distill-Qwen-9B-Q5_K_M.gguf}"
+LLM_SMALL_MODEL_FILE="${LLM_SMALL_MODEL_FILE:-/home/dank/models/MiMo-Q6K/MiMo-V2.6-Distill-Qwen-9B-Q6_K.gguf}"
 LLM_SMALL_RUNTIME="${LLM_SMALL_RUNTIME:-/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server}"
-# The projector IS the vision capability here: the Q5_K_M GGUF ships no `v.*`
+# The projector IS the vision capability here: the Q6_K GGUF ships no `v.*`
 # tensors, so a deploy that starts without this file silently ships a
 # text-only endpoint. Checked unconditionally, like frank-large's.
-LLM_SMALL_MMPROJ="${LLM_SMALL_MMPROJ:-/home/dank/models/MiMo-Q5KM/mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf}"
+LLM_SMALL_MMPROJ="${LLM_SMALL_MMPROJ:-/home/dank/models/MiMo-Q6K/mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf}"
 
 deploy_llm_small() {
     # Refuse rather than restart-loop: a unit whose runtime or payload is
diff --git a/scripts/download-frank-small.sh b/scripts/download-frank-small.sh
index 3831ad0..1d69ead 100755
--- a/scripts/download-frank-small.sh
+++ b/scripts/download-frank-small.sh
@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 # Download the frank-small payload for llama.cpp on the RTX 3090:
-# bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q5_K_M plus its vision projector
+# bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K plus its vision projector
 # (the GGUF carries no `v.*` tensors — the tower lives only in the mmproj, so
 # without this file the endpoint is text-only by construction). Public repo —
 # no auth header, and never a token on the command line (it is world-readable
@@ -11,10 +11,11 @@
 # then byte count and the Hub LFS sha256. Idempotent: complete files are
 # skipped.
 #
-# The Q6_K file this endpoint served until 2026-10-01 night stays on disk as
-# the rollback target (7793710624 B, LFS oid
-# ef96d05a2ddf2cbb450d1af1ac3860ec769d3575bafa70692ee5609bda3fad7d) — re-fetch
-# it from the same repo with the same recipe if it is ever needed again.
+# 2026-10-03: the rung is Q6_K again — the freed third slot funds exact f16 V
+# AND the higher quant. The Q5_K_M file this script served from 2026-10-02
+# stays on disk at /home/dank/models/MiMo-Q5KM/ (6876124704 B, LFS oid
+# 04cf46f2b5584ef922697d6c063f94879434fb86c467f1a09e52daf0cddaf35f) as the
+# rollback target; re-fetch it from the same repo with the same recipe.
 #
 # Usage:
 #   scripts/download-frank-small.sh [DEST_DIR] [--verify-only]
@@ -31,11 +32,11 @@ for arg in "$@"; do
         *) DEST="$arg" ;;
     esac
 done
-DEST="${DEST:-/home/dank/models/MiMo-Q5KM}"
+DEST="${DEST:-/home/dank/models/MiMo-Q6K}"
 
 # name bytes sha256
 FILES=(
-  "MiMo-V2.6-Distill-Qwen-9B-Q5_K_M.gguf 6876124704 04cf46f2b5584ef922697d6c063f94879434fb86c467f1a09e52daf0cddaf35f"
+  "MiMo-V2.6-Distill-Qwen-9B-Q6_K.gguf 7793710624 ef96d05a2ddf2cbb450d1af1ac3860ec769d3575bafa70692ee5609bda3fad7d"
   "mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf 918166048 ff348f3180a63188aa7285db85f550fe38acb61dd013c599eb8bad08d2cc2576"
 )
 
diff --git a/scripts/frank-small.env b/scripts/frank-small.env
index da5b7f3..7c28b51 100644
--- a/scripts/frank-small.env
+++ b/scripts/frank-small.env
@@ -1,5 +1,12 @@
 # frank-small — llama.cpp (master, CUDA sm_86) serving
-# bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q5_K_M on the RTX 3090, :7771.
+# bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K on the RTX 3090, :7771.
+#
+# 2026-10-03 (Frank, second move): the rung went Q5_K_M -> Q6_K with the pool
+# HELD at 401,408. The freed third slot funded exact f16 V first; the ~3.5 GiB
+# still free funds the +875 MiB of weights (file delta 7,793,710,624 -
+# 6,876,124,704). Projected landing ~2.7 GiB free — inside the 2-3 GiB floor,
+# so MEASURE after the boot; if it lands under 2 GiB, step the pool down one
+# 12,288-token (384 MiB) increment.
 #
 # 2026-10-03 (Frank): TWO streams instead of three, each one WIDE — 200,704
 # tokens per conversation, above the 200,700 the harness compacts at — and the
@@ -38,12 +45,14 @@
 # and the third slot is gone. The flags stay explicit so the choice is visible
 # in the argv either way.
 LLAMA_BIN=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server
-MODEL_FILE=/home/dank/models/MiMo-Q5KM/MiMo-V2.6-Distill-Qwen-9B-Q5_K_M.gguf
+MODEL_FILE=/home/dank/models/MiMo-Q6K/MiMo-V2.6-Distill-Qwen-9B-Q6_K.gguf
 
-# Vision: the Q5_K_M GGUF ships no `v.*` tensors, so the projector file IS the
-# vision capability (sha256 ff348f31..., 918,166,048 B, fetched by
-# scripts/download-frank-small.sh). Empty string = text-only on purpose.
-MMPROJ_FILE=/home/dank/models/MiMo-Q5KM/mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf
+# Vision: the Q6_K GGUF ships no `v.*` tensors either, so the projector file
+# IS the vision capability (sha256 ff348f31..., 918,166,048 B, fetched by
+# scripts/download-frank-small.sh; hardlinked into this dir from MiMo-Q5KM/,
+# same bytes — the Q6_K dir is self-contained). Empty string = text-only on
+# purpose.
+MMPROJ_FILE=/home/dank/models/MiMo-Q6K/mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf
 
 # Fleet endpoint: same port and alias as every frank-small before it, so the
 # harness models.yml id and the homepage probe do not move.
diff --git a/scripts/serve-frank-small.sh b/scripts/serve-frank-small.sh
index 9069b97..7e7f907 100755
--- a/scripts/serve-frank-small.sh
+++ b/scripts/serve-frank-small.sh
@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# Serve bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF (Q5_K_M) as frank-small on
+# Serve bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF (Q6_K) as frank-small on
 # Dankclaw's RTX 3090 via llama.cpp (master build, CUDA sm_86).
 #
 # 2026-10-01 night (Frank): swapped from SGLang + INT8-W8A16-AutoRound
@@ -12,7 +12,7 @@
 # Architecture: qwen3_5 hybrid — 32 layers, 8 full-attention + 24 Gated
 # DeltaNet, native 262144 window. KV lives only in the 8 attention layers;
 # the DeltaNet state is per-slot fixed size. Vision comes from the repo's
-# separate projector (the Q5_K_M GGUF carries no `v.*` tensors at all), so
+# separate projector (the Q6_K GGUF carries no `v.*` tensors at all), so
 # --mmproj is what gives this endpoint eyes; MMPROJ_FILE="" is the documented
 # text-only opt-out.
 #
@@ -33,7 +33,7 @@ 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/MiMo-Q5KM/MiMo-V2.6-Distill-Qwen-9B-Q5_K_M.gguf}"
+: "${MODEL_FILE:=/home/dank/models/MiMo-Q6K/MiMo-V2.6-Distill-Qwen-9B-Q6_K.gguf}"
 : "${ALIAS:=frank-small}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7771}"
@@ -54,7 +54,7 @@ fi
 : "${NGL:=99}"
 # Vision projector. No colon on purpose: an explicitly empty value means
 # "text-only, on purpose" and must NOT be replaced by the default path.
-: "${MMPROJ_FILE=/home/dank/models/MiMo-Q5KM/mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf}"
+: "${MMPROJ_FILE=/home/dank/models/MiMo-Q6K/mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.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
diff --git a/tests/frank_small_unit.bats b/tests/frank_small_unit.bats
index 41a2156..0b7817c 100755
--- a/tests/frank_small_unit.bats
+++ b/tests/frank_small_unit.bats
@@ -1,7 +1,7 @@
 #!/usr/bin/env bats
 # Seam: the frank-small llama.cpp root unit on dankclaw.
 # frank-small is the RTX 3090 endpoint; since 2026-10-01 night it serves
-# bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q5_K_M via a CUDA (sm_86) build of
+# bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q6_K via a CUDA (sm_86) build of
 # llama.cpp master, chosen because it is the only runtime here that moves K and
 # V independently. Since 2026-10-03 it runs TWO unquantized contexts of
 # 200,704 tokens each and carries a vision projector, and the card must keep
@@ -16,7 +16,7 @@ SERVE="$REPO_ROOT/scripts/serve-frank-small.sh"
 ENV_FILE="$REPO_ROOT/scripts/frank-small.env"
 REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
 ENV_LARGE="$REPO_ROOT/scripts/frank-large.env"
-TARGET_STUB="MiMo-V2.6-Distill-Qwen-9B-Q5_K_M.gguf"
+TARGET_STUB="MiMo-V2.6-Distill-Qwen-9B-Q6_K.gguf"
 # Same basename as the shipped projector: the test env repoints it into $STAGE.
 MM_STUB="mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf"
 
@@ -79,9 +79,9 @@ argv_value() {
     grep -q 'FRANK_SMALL_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-small.env' "$UNIT"
 }
 
-@test "the shipped env points at the llama.cpp runtime and the Q5_K_M GGUF" {
+@test "the shipped env points at the llama.cpp runtime and the Q6_K GGUF" {
     grep -qE '^LLAMA_BIN=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server$' "$ENV_FILE"
-    grep -qE "^MODEL_FILE=/home/dank/models/MiMo-Q5KM/$TARGET_STUB$" "$ENV_FILE"
+    grep -qE "^MODEL_FILE=/home/dank/models/MiMo-Q6K/$TARGET_STUB$" "$ENV_FILE"
 }
 
 @test "the deployer gates on exactly the payload paths the env file ships" {
@@ -169,7 +169,7 @@ argv_value() {
 }
 
 @test "vision ships by default and MMPROJ_FILE empty opts out of the image path" {
-    # The Q5_K_M GGUF carries no `v.*` tensors, so the projector argument IS
+    # The Q6_K GGUF carries no `v.*` tensors, so the projector argument IS
     # the vision capability: no flag, no eyes.
     serve_argv
     [ "$status" -eq 0 ]