Qwen3-235B-A22B-Thinking-2507-mixed-3-5bit
mlx-community/Qwen3-235B-A22B-Thinking-2507-mixed-3-5bit
Text generation · mlx
5-bit Open on Hugging Face
Parameters
235B
Weights (est.)
≈ 162 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-Thinking-2507-mixed-3-5bit --prompt "Hello"
Details
- Base model
- Qwen/Qwen3-235B-A22B-Thinking-2507 (quantized)
- Vendor
- Qwen
- Task
- Text generation
- Quantisation
- 5-bit
- Licence
- apache-2.0
- Downloads
- 25 in the last 30 days · 795 all time · 1 likes
- Published
- 2025-07-25 · updated 2025-07-25 (1y ago)
- Tags
- qwen3_moe
Other MLX builds of Qwen/Qwen3-235B-A22B-Thinking-2507
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3-235B-A22B-Thinking-2507-3bit-DWQ | 3-bit DWQ | ≈ 103 GB | 128 GB+ | 40 |
| Qwen3-235B-A22B-Thinking-2507-3bit | 3-bit | ≈ 103 GB | 128 GB+ | 30 |
| Qwen3-235B-A22B-Thinking-2507-4bit | 4-bit | ≈ 132 GB | 192 GB+ | 15K |
| Qwen3-235B-A22B-Thinking-2507-4bit-DWQ | 4-bit DWQ | ≈ 132 GB | 192 GB+ | 33 |
| Qwen3-235B-A22B-Thinking-2507-mixed-3-5bit (this one) | 5-bit | ≈ 162 GB | 192 GB+ | 25 |
| Qwen3-235B-A22B-Thinking-2507-5bit | 5-bit | ≈ 162 GB | 192 GB+ | 23 |
| Qwen3-235B-A22B-Thinking-2507-8bit | 8-bit | ≈ 250 GB | 512 GB+ | 80 |