Qwen3 Coder 30B-A3B Instruct
Alibaba · 30.5B (3.3B active, MoE) · up to 256K context · apache-2.0
This is the current go-to local coding model for a 32GB Mac, trading some raw code-quality against Qwen2.5-Coder-32B for much faster generation. Its 262K context window means it can hold a real codebase's worth of files in one session, which the dense coder can't do as cheaply.
On a M4 Pro with 48 GB
macOS9.6 GBweights24.8 GBKV cache0.8 GBheadroom12.8 GB
- Weights
- 24.8 GB
- KV cache
- 0.8 GB
- Usable RAM
- 38.4 GB
- Headroom
- 12.8 GB
- Generation
- 79.4 tok/sest.
- Prompt processing
- 274 tok/sest.
- First token (1K prompt)
- 3.7 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 | 17.2 GB | 18.0 GB | FITS · 20.4 GB FREE | 115 tok/s | Qwen3-Coder-30B-A3B-Instruct-4bit |
| q6 | 24.8 GB | 25.6 GB | FITS · 12.8 GB FREE | 79.4 tok/s | Qwen3-Coder-30B-A3B-Instruct-6bit |
| q8 | 32.4 GB | 33.2 GB | TIGHT · 5.2 GB FREE | 60.7 tok/s | Qwen3-Coder-30B-A3B-Instruct-8bit |
We never host weights. Every link goes to Hugging Face.
Run it
Chat
mlx_lm.chat --model mlx-community/Qwen3-Coder-30B-A3B-Instruct-6bitServe an OpenAI-compatible endpoint
mlx_lm.server --model mlx-community/Qwen3-Coder-30B-A3B-Instruct-6bit --port 8080How far can you push the context
2K tokensFITS · 13.4 GB FREE
cache 0.2 GB
8K tokensFITS · 12.8 GB FREE
cache 0.8 GB
32K tokensFITS · 10.4 GB FREE
cache 3.2 GB
128K tokensTIGHT · 0.7 GB FREE
cache 12.9 GB
Which Macs run this
| Chip | Smallest RAM that fits | Speed est. |
|---|---|---|
| M1 | no configuration | — |
| M1 Pro | no configuration | — |
| M1 Max | 64 GB | 118 tok/s |
| M1 Ultra | 64 GB | 242 tok/s |
| M2 | no configuration | — |
| M2 Pro | no configuration | — |
| M2 Max | 64 GB | 119 tok/s |
| M2 Ultra | 64 GB | 245 tok/s |
| M3 | no configuration | — |
| M3 Pro | 36 GB | 42.0 tok/s |
| M3 Max (14-core CPU) | 36 GB | 87.3 tok/s |
| M3 Max (16-core CPU) | 48 GB | 119 tok/s |
| M3 Ultra | 96 GB | 254 tok/s |
| M4 | no configuration | — |
| M4 Pro | 48 GB | 79.4 tok/s |
| M4 Max (14-core CPU) | 36 GB | 124 tok/s |
| M4 Max (16-core CPU) | 48 GB | 167 tok/s |
| M5 | no configuration | — |
| M5 Prounverified | 48 GB | 90.5 tok/s |
| M5 Maxunverified | 36 GB | 190 tok/s |