---
license: apache-2.0
language: en
base_model:
- empero-ai/Qwen3.8-2B-Distill
base_model_relation: quantized
quantized_by: Atomic-Germ
pipeline_tag: image-text-to-text
tags:
- transformers
- qwen3_5_text
- image-text-to-text
- conversational
- q4nx
- quantized
- npu2
- fastflowlm
- fastflow
- flm
- empero-ai
- qwen3.8
- distillation
- reasoning
---
# Qwen3.8-2B-Distill-NPU2

**FastFlowLM Q4NX conversion of [`empero-ai/Qwen3.8-2B-Distill`](https://huggingface.co/empero-ai/Qwen3.8-2B-Distill)** 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 | [`empero-ai/Qwen3.8-2B-Distill`](https://huggingface.co/empero-ai/Qwen3.8-2B-Distill) |
| Source GGUF | `Qwen3.8-2B-Q8_0.gguf` |
| Weights | `model.q4nx` (2.32 GB) |
| Modality | language / vision |
| FLM version | `1.0.1` |
| Converted | 2026-08-24 |

## 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`

```bash
uv tool install flm-add
flm-add Atomic-Germ/Qwen3.8-2B-Distill-NPU2 --family qwen3.5 --tag qwen3.8-distill:2b
FLM_CONFIG_PATH="$HOME/.config/flm/model_list.json" FLM_XCLBIN_PATH="$HOME/.config/flm" flm run qwen3.8-distill:2b
```

## 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 |


---

## Source model card

See the original model card: [empero-ai/Qwen3.8-2B-Distill](https://huggingface.co/empero-ai/Qwen3.8-2B-Distill)