Qwen3 8B
Alibaba · 8.2B · up to 40K context · apache-2.0
This is currently the best all-round 8B for a 16GB Mac, with the thinking-mode toggle giving you a manual quality/speed dial. At 4-bit it leaves enough memory free to keep a coding editor and a few Chrome tabs open.
On a M4 Pro with 48 GB
macOS9.6 GBweights8.7 GBKV cache1.2 GBheadroom28.5 GB
- Weights
- 8.7 GB
- KV cache
- 1.2 GB
- Usable RAM
- 38.4 GB
- Headroom
- 28.5 GB
- Generation
- 24.4 tok/sest.
- Prompt processing
- 110 tok/sest.
- First token (1K prompt)
- 9.3 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 | 4.6 GB | 5.8 GB | FITS · 32.6 GB FREE | 46.2 tok/s | Qwen3-8B-4bit |
| q6 | 6.7 GB | 7.9 GB | FITS · 30.5 GB FREE | 32.0 tok/s | Qwen3-8B-6bit |
| q8 | 8.7 GB | 9.9 GB | FITS · 28.5 GB FREE | 24.4 tok/s | Qwen3-8B-8bit |
We never host weights. Every link goes to Hugging Face.
Run it
Chat
mlx_lm.chat --model mlx-community/Qwen3-8B-8bitServe an OpenAI-compatible endpoint
mlx_lm.server --model mlx-community/Qwen3-8B-8bit --port 8080How far can you push the context
2K tokensFITS · 29.4 GB FREE
cache 0.3 GB
8K tokensFITS · 28.5 GB FREE
cache 1.2 GB
32K tokensFITS · 24.9 GB FREE
cache 4.8 GB
Which Macs run this
| Chip | Smallest RAM that fits | Speed est. |
|---|---|---|
| M1 | 16 GB | 5.6 tok/s |
| M1 Pro | 16 GB | 17.4 tok/s |
| M1 Max | 32 GB | 36.3 tok/s |
| M1 Ultra | 64 GB | 74.4 tok/s |
| M2 | 16 GB | 8.4 tok/s |
| M2 Pro | 16 GB | 17.7 tok/s |
| M2 Max | 32 GB | 36.7 tok/s |
| M2 Ultra | 64 GB | 75.3 tok/s |
| M3 | 16 GB | 8.4 tok/s |
| M3 Pro | 18 GB | 12.9 tok/s |
| M3 Max (14-core CPU) | 36 GB | 26.9 tok/s |
| M3 Max (16-core CPU) | 48 GB | 36.7 tok/s |
| M3 Ultra | 96 GB | 78.0 tok/s |
| M4 | 16 GB | 10.2 tok/s |
| M4 Pro | 24 GB | 24.4 tok/s |
| M4 Max (14-core CPU) | 36 GB | 38.1 tok/s |
| M4 Max (16-core CPU) | 48 GB | 51.4 tok/s |
| M5 | 16 GB | 13.2 tok/s |
| M5 Prounverified | 24 GB | 27.8 tok/s |
| M5 Maxunverified | 36 GB | 58.5 tok/s |