Qwen3-235B-A22B-Instruct-2507-4bit
mlx-community/Qwen3-235B-A22B-Instruct-2507-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
235B
Weights (est.)
≈ 132 GB
Mac memory (est.)
192 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/Qwen3-235B-A22B-Instruct-2507-4bit --prompt "Hello"
Details
- Base model
- Qwen/Qwen3-235B-A22B-Instruct-2507 (quantized)
- Vendor
- Qwen
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 5.1K in the last 30 days · 106K all time · 3 likes
- Published
- 2025-07-22 · updated 2025-07-22 (1y ago)
- Tags
- qwen3_moe
Other MLX builds of Qwen/Qwen3-235B-A22B-Instruct-2507
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3-235B-A22B-Instruct-2507-3bit | 3-bit | ≈ 103 GB | 128 GB+ | 62 |
| Qwen3-235B-A22B-Instruct-2507-4bit (this one) | 4-bit | ≈ 132 GB | 192 GB+ | 5.1K |
| Qwen3-235B-A22B-Instruct-2507-5bit | 5-bit | ≈ 162 GB | 192 GB+ | 148 |
| Qwen3-235B-A22B-Instruct-2507-6bit | 6-bit | ≈ 191 GB | 256 GB+ | 45 |
| Qwen3-235B-A22B-Instruct-2507-8bit | 8-bit | ≈ 250 GB | 512 GB+ | 609 |