Hy4 family Nace quants
Collection
Nace quants of Tencent Hy4 models: GGUF and MLX. • 6 items • Updated
How to use nace-ai/Hy4-flash-MLX-4.6bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download nace-ai/Hy4-flash-MLX-4.6bit --local-dir Hy4-flash-MLX-4.6bit
A 125.20 GB quant of Hy4-flash from Nace.AI, 4.6 bits per weight.
On a fixed 100-question LiveCodeBench release_v6 subset with an 8,192-token cap, it solved 39/100 questions, the same as the 4-bit pack at a smaller size.
37 measured Hy4-flash variants on the same 11 texts, 5,621 scored tokens. Chart sizes use text-weight payload, including required Engram tables, excluding vision/MTP. Complete weight-file sizes and exact scores are in the comparison data.
Download the model and run it with the bundled loader:
hf download nace-ai/Hy4-flash-MLX-4.6bit --local-dir Hy4-flash-MLX-4.6bit
cd Hy4-flash-MLX-4.6bit
pip install -r requirements-macos.txt
python run_mlx.py --prompt 'What is the capital of France?' --max-tokens 32
4-bit
Base model
tencent/Hy4-flash