MLX Community · First MLX build 9 Oct 2025
Qwen3-VL-235B-A22B-Instruct
MLX
apache-2.0
A model, with 2 MLX builds, from 4-bit to 3-bit.
- Parameters
- — Not published
- Quantisation
- 4-bit Qwen3-VL-235B-A22B-Instruct-4bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 111 This build, last 30 days
- Task
- —
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Qwen3-VL-235B-A22B-Instruct-4bitMLX builds
2 on mlx-community| Qwen3-VL-235B-A22B-Instruct-4bit | 4-bit | — | — | 111 |
|---|---|---|---|---|
| Qwen3-VL-235B-A22B-Instruct-3bit | 3-bit | — | — | 65 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.