4-bit Open on Hugging Face
Parameters
396B
Weights (est.)
≈ 223 GB
Mac memory (est.)
256 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Qwen3.5-397B-A17B-nvfp4 --prompt "Hello"
Details
- Base model
- Qwen/Qwen3.5-397B-A17B (quantized)
- Vendor
- Qwen
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 1.6K in the last 30 days · 12K all time · 6 likes
- Published
- 2026-02-16 · updated 2026-02-16 (8mo ago)
- Languages
- multilingual
- Tags
- qwen3_5_moe, 4bit, nvfp4, quantized, mixture-of-experts, apple-silicon
Other MLX builds of Qwen/Qwen3.5-397B-A17B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3.5-397B-A17B-nvfp4 (this one) | 4-bit | ≈ 223 GB | 256 GB+ | 1.6K |
| Qwen3.5-397B-A17B-8bit | 8-bit | ≈ 422 GB | 512 GB+ | 165 |