Models
OpenFlowLM Q4NX tune of Atomic-Germ/Qwen3.6-35B-A3B-NPU2 for AMD XDNA NPU inference.
This repository contains a quantized Q4NX port of the model, compiled for the OpenFlowLM (OFLM) runtime. It is not a GGUF file.
| Item | Value |
|---|---|
| Source model | Atomic-Germ/Qwen3.6-35B-A3B-NPU2 |
| Weights | model.q4nx (22.14 GB) |
| Modality | language / vision |
| OFLM version | 0.1.0 |
| Converted | 2026-09-28 |
Install and run
OpenFlowLM-Next comes with oflm add
oflm add Atomic-Germ/Qwen3.8-Distilled-Q4_K-35B-A3B-NPU2 --family qwen3.6-moe
Files
| File | Description |
|---|---|
model.q4nx |
Quantized weights (Q8_0 / Q4_1 / BF16) |
config.json |
OFLM 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: Atomic-Germ/Qwen3.6-35B-A3B-NPU2