MTPLX / Apple Silicon optimized Q6G64 conversion of:
petruhonk/Qwen3.8-9B-Distill-uncensored-heretic
Repository:
xy10086/Qwen3.8-9B-Distill-Uncensored-Heretic-MTPLX-Q6G64
Source model:
petruhonk/Qwen3.8-9B-Distill-uncensored-heretic
Upstream model:
empero-ai/Qwen3.8-9B-Distill
The source repository did not include the vision preprocessing sidecars
required by MTPLX. Matching preprocessor_config.json and
video_preprocessor_config.json were restored from the upstream
empero-ai/Qwen3.8-9B-Distill repository.
The source vision weights were preserved by MTPLX Forge and stored in
model-vision.safetensors.
Main language-model trunk:
MTP:
Vision:
Forge recipe: forge-recipe.json
| Mode | Decode tok/s |
|---|---|
| AR | 32.42 |
| D1 | 58.91 |
| D2 | 71.70 |
| D3 | 70.90 |
| Depth | Avg decode tok/s | Avg TTFT |
|---|---|---|
| D1 | 49.41 | 0.159 s |
| D2 | 50.73 | 0.134 s |
| D3 | 46.38 | 0.135 s |
See benchmarks.json for the machine-readable summary.
Pull:
mtplx pull xy10086/Qwen3.8-9B-Distill-Uncensored-Heretic-MTPLX-Q6G64
Serve:
mtplx serve \
--model xy10086/Qwen3.8-9B-Distill-Uncensored-Heretic-MTPLX-Q6G64 \
--host 127.0.0.1 \
--port 8000 \
--profile sustained \
--generation-mode mtp \
--depth 2 \
--context-window 32768 \
--max-tokens 8192 \
--reasoning off \
--reasoning-effort low \
--no-auth \
--yes
OpenAI-compatible endpoint:
http://127.0.0.1:8000/v1
This model is derived from a low-refusal / censorship-ablated checkpoint. Lower refusal behavior does not imply higher factual accuracy.
Medical, legal, financial and other high-stakes outputs should be independently verified.
petruhonk/Qwen3.8-9B-Distill-uncensored-hereticempero-ai/Qwen3.8-9B-DistillApache-2.0. Review the upstream repositories for their attribution and license requirements as well.
model-00001-of-00002.safetensors 5.4 GBmodel-00002-of-00002.safetensors 1.9 GBmodel-vision.safetensors 912 MBpetruhonk/Qwen3.8-9B-Distill-uncensored-heretic