8-bit Open on Hugging Face
Parameters
397B
Weights (est.)
≈ 422 GB
Mac memory (est.)
512 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-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/Qwen3.5-397B-A17B-8bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- Qwen/Qwen3.5-397B-A17B (quantized)
- Vendor
- Qwen
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 165 in the last 30 days · 119K all time · 5 likes
- Published
- 2026-02-16 · updated 2026-02-20 (8mo ago)
- Tags
- qwen3_5_moe
Other MLX builds of Qwen/Qwen3.5-397B-A17B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3.5-397B-A17B-nvfp4 | 4-bit | ≈ 223 GB | 256 GB+ | 1.6K |
| Qwen3.5-397B-A17B-8bit (this one) | 8-bit | ≈ 422 GB | 512 GB+ | 165 |