Hy-MT2-7B-NPU2

OpenFlowLM Q4NX conversion of tencent/Hy-MT2-7B-FP8 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	tencent/Hy-MT2-7B-FP8
Source GGUF	Hy-MT2-7B.Q8_0.gguf
Weights	model.q4nx (5.35 GB)
Modality	language
OFLM version	0.1.0
Converted	2026-10-01

Install and run

This repository works with oflm-add, a small installer that copies the model into the OpenFlowLM user directory and registers the tag. It never modifies the system OpenFlowLM install.

pip install oflm-add or uv tool install oflm-add

uv tool install oflm-add
oflm-add Atomic-Germ/Hy-MT2-7B-NPU2 --family qwen3.5 --xclbin-from Hy-MT2-7B-NPU2
OFLM_CONFIG_PATH="$HOME/.config/oflm/model_list.json" OFLM_XCLBIN_PATH="$HOME/.config/oflm" oflm run Hy-MT2-7B-NPU2

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

---

Source model card

See the original model card: tencent/Hy-MT2-7B-FP8