Qwen3.8-9B-Distilled-Heretic-NPU2
FastFlowLM Q4NX conversion of petruhonk/Qwen3.8-9B-Distill-uncensored-heretic for AMD XDNA NPU inference.
This repository contains a quantized Q4NX port of the model, compiled for the FastFlowLM (FLM) runtime. It is not a GGUF file.
| Item | Value |
|---|---|
| Source model | petruhonk/Qwen3.8-9B-Distill-uncensored-heretic |
| Weights | model.q4nx (7.11 GB) |
| Modality | language |
| FLM version | 1.0.1 |
| Converted | 2026-08-30 |
Install and run
This repository works with flm-add, a small installer that copies the model
into the FastFlowLM user directory and registers the tag. It never
modifies the system FastFlowLM install.
pip install flm-add or uv tool install flm-add
uv tool install flm-add
flm-add Atomic-Germ/Qwen3.8-Distilled-Heretic-9B-NPU2 --family qwen3.5
FLM_CONFIG_PATH="$HOME/.config/flm/model_list.json" FLM_XCLBIN_PATH="$HOME/.config/flm" flm run qwen3.8-distilled-heretic:9b
Files
| File | Description |
|---|---|
model.q4nx |
Quantized weights (Q8_0 / Q4_1 / BF16) |
config.json |
FLM runtime configuration |
tokenizer.json |
Tokenizer vocabulary |
tokenizer_config.json |
Tokenizer configuration |
chat_template.jinja |
Chat template |
vision_weight.q4nx |
Vision model |
results/ |
FLM-Test results |
Source model card
See the original model card: petruhonk/Qwen3.8-9B-Distill-uncensored-heretic