by openai-community
⬇ 29.8M♥ 3.9K
Qwen3.5-397B-A17B-VQ-3.5bpw
- Task
- Text generation
- Category
- Language
- License
- Apache 2.0
- Commercial use
- Yes
Permissive license: commercial use is allowed; keep the copyright and license notice. - Size
- About 397 billion parameters
- Memory to load
- ~239 GB (estimate)
- Format
- MLX
- Runs on
- CPU
- Access
- Open download
- Downloads (last 30 days)
- 0
- Likes
- 0
- Last updated
- October 2, 2026
How to run it
This is an MLX build for Apple silicon Macs; run it with Apple's MLX framework (mlx-lm for language models).
Plan for roughly 239 GB of memory to load it (our estimate from its size and format).
The model card on Hugging Face has the exact usage code.
Where to run it
In the cloud
Needs about 239 GB: more than one GPU, for example 3 × 80 GB A100 or H100.
- RunPod · rent a GPU by the hour (affiliate link)
Related text generation models
Data from Hugging Face's public API, last checked October 2, 2026. Downloads are Hugging Face's count for the last 30 days.