Qwen3 235B-A22B
Alibaba · 235B (22B active, MoE) · up to 40K context · apache-2.0
A genuinely usable frontier-scale MoE on a 192GB or 256GB Mac Studio, with 22B active parameters keeping generation speed reasonable despite the huge total. It sits between GPT-OSS-120B and DeepSeek-V3 in both memory demand and benchmark quality.
On a M4 Pro with 48 GB
macOS9.6 GBweights249.7 GBKV cache1.6 GBover212.9 GB
- Weights
- 249.7 GB
- KV cache
- 1.6 GB
- Usable RAM
- 38.4 GB
- Headroom
- 0.0 GB
- Generation
- 9.1 tok/sest.
- Prompt processing
- 41.0 tok/sest.
- First token (1K prompt)
- 24.9 sest.
Decode speed is bandwidth ÷ active weight bytes, at 273 GB/s and 78% efficiency. These are modelled figures, not measurements.
Every quantization, on your Mac
| Quant | Weights | + KV | Verdict | Speed est. | Repo |
|---|---|---|---|---|---|
| q4 | 132.2 GB | 133.8 GB | OVER BY 95.4 GB | 17.2 tok/s | Qwen3-235B-A22B-4bit |
| q8 | 249.7 GB | 251.3 GB | OVER BY 212.9 GB | 9.1 tok/s | Qwen3-235B-A22B-4bit-DWQ |
We never host weights. Every link goes to Hugging Face.
Run it
Chat
mlx_lm.chat --model mlx-community/Qwen3-235B-A22B-4bit-DWQServe an OpenAI-compatible endpoint
mlx_lm.server --model mlx-community/Qwen3-235B-A22B-4bit-DWQ --port 8080How far can you push the context
2K tokensOVER BY 211.7 GB
cache 0.4 GB
8K tokensOVER BY 212.9 GB
cache 1.6 GB
32K tokensOVER BY 217.6 GB
cache 6.3 GB
Which Macs run this
| Chip | Smallest RAM that fits | Speed est. |
|---|---|---|
| M1 | no configuration | — |
| M1 Pro | no configuration | — |
| M1 Max | no configuration | — |
| M1 Ultra | no configuration | — |
| M2 | no configuration | — |
| M2 Pro | no configuration | — |
| M2 Max | no configuration | — |
| M2 Ultra | no configuration | — |
| M3 | no configuration | — |
| M3 Pro | no configuration | — |
| M3 Max (14-core CPU) | no configuration | — |
| M3 Max (16-core CPU) | no configuration | — |
| M3 Ultra | 512 GB | 29.1 tok/s |
| M4 | no configuration | — |
| M4 Pro | no configuration | — |
| M4 Max (14-core CPU) | no configuration | — |
| M4 Max (16-core CPU) | no configuration | — |
| M5 | no configuration | — |
| M5 Prounverified | no configuration | — |
| M5 Maxunverified | no configuration | — |