serverAppConfigs/docs/LLM/kingjones-strix-mtp.md

type, title, description, tags, timestamp

type	title	description	tags	timestamp
reference	kingjones Qwen3.8-27B ROCmFP4 STRIX MTP on Dankclaw	kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP served by the CIRU ROCmFPX llama.cpp runtime on the Strix Halo iGPU. Dense model with a standalone MTP Q4_0 draft head. frank-default-large.	llama.cpp rocm dankclaw gfx1151 kingjones rocmfp4 mtp	2026-08-24

kingjones Qwen3.8-27B ROCmFP4 STRIX MTP on Dankclaw

Active again 2026-09-01. The kingjones ROCmFP4 STRIX MTP payload is restored as frank-default-large after the Q8_0 AGENT experiment. The Q8_0 model was retired because it crashed before serving. The Q6 AGENT model, standalone MTP draft, Q8 projector, and PromptForge runtime are now active.

This page documents the active model and its runbook.

frank-default-large (port 7770) serves Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP from kingjones777 on Hugging Face. It is a dense Qwen3.8-27B, abliterated (uncensored), quantized to the ROCmFP4 Q6 AGENT format (ftype 114). The MTP speculative head ships as a separate Q4_0 draft GGUF, so a bundled-head auto-detect does not apply here; the head is loaded with --model-draft.

Model Files

The card ships six text files plus the vision projector. The service uses the Q6 AGENT file (requested for the fleet), the separate MTP draft head and the Q8 vision projector (mmproj-Qwen3.8-27B-Q8_0.gguf).

File	Size
Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf	23.15 GiB
mtp-Qwen3.8-27B-Q4_0.gguf (draft head)	1.56 GiB
mmproj-Qwen3.8-27B-Q8_0.gguf (vision)	0.59 GiB

Store the files under /home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP/.

Speculative Decoding

Dense model, so the finding measured on the dense Qwen3.8 family holds: MTP alone at --spec-draft-n-max 4 is the knee. ngram under MTP hurts (measured -4 to -5 t/s on the v3; see ciru-activefpx-promptforge). The draft head is a separate file loaded via:

--spec-type draft-mtp
--model-draft mtp-Qwen3.8-27B-Q4_0.gguf
--spec-draft-n-max 4
--spec-draft-n-min 0
--spec-draft-p-min 0.0

The draft head loads on ROCm1 with full offload (--spec-draft-ngl 999) and f16 KV.

Launch Excerpt

The key flags on the CIRU ROCmFPX runtime:

llama-server \
  -m Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf \
  --mmproj mmproj-Qwen3.8-27B-Q8_0.gguf \
  --chat-template-file chat-template.jinja \
  --chat-template-kwargs '{"enable_thinking":true,"preserve_thinking":true}' \
  -ngl 999 -dev ROCm0 -c 196608 -np 1 \
  -b 8192 -ub 8192 -ctxcp 32 \
  --spec-type draft-mtp --model-draft mtp-Qwen3.8-27B-Q4_0.gguf \
  --spec-draft-ngl 999 --spec-draft-n-max 4 \
  -fa on --no-mmap --cache-type-k f16 --cache-type-v f16

Known Issues

1. GPU only: Vulkan, CUDA, and CPU cannot load these files.
2. --spec-draft-n-max defaults to 16; set 4.
3. reasoning_effort: "none" throws in the Qwen API. Use enable_thinking: false instead.
4. Small max_tokens with thinking on returns empty content. The Sharp template drives thinking on by default (effort medium).
5. preserve_thinking:true (in chat_template_kwargs) keeps <think> blocks in recorded assistant messages. preserve_thinking:false strips them. See deployment for the chat_format/reasoning_format pairing (peg-native + deepseek) the Pi agent expects from this endpoint.

See Also

• deployment — deploy and update process
• ciru-activefpx-promptforge — the retired v3 page
• Dankclaw System Specs — the box
• frank-redo-2026-08-17 — fleet topology history