Qwen3 1.7B
Alibaba · 1.7B · up to 40K context · apache-2.0
A comfortable fit on any 8GB Mac and effectively free to run on 16GB. The thinking mode helps on logic puzzles but roughly doubles response time, so it's a tradeoff you feel.
On a M4 Pro with 48 GB
macOS9.6 GBweights3.4 GBKV cache0.9 GBheadroom34.1 GB
- Weights
- 3.4 GB
- KV cache
- 0.9 GB
- Usable RAM
- 38.4 GB
- Headroom
- 34.1 GB
- Generation
- 62.6 tok/sest.
- Prompt processing
- 531 tok/sest.
- First token (1K prompt)
- 1.9 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 | 1.0 GB | 1.9 GB | FITS · 36.5 GB FREE | 223 tok/s | Qwen3-1.7B-4bit |
| q8 | 1.8 GB | 2.7 GB | FITS · 35.7 GB FREE | 118 tok/s | Qwen3-1.7B-8bit |
| bf16 | 3.4 GB | 4.3 GB | FITS · 34.1 GB FREE | 62.6 tok/s | Qwen3-1.7B-bf16 |
We never host weights. Every link goes to Hugging Face.
Run it
Chat
mlx_lm.chat --model mlx-community/Qwen3-1.7B-bf16Serve an OpenAI-compatible endpoint
mlx_lm.server --model mlx-community/Qwen3-1.7B-bf16 --port 8080How far can you push the context
2K tokensFITS · 34.8 GB FREE
cache 0.2 GB
8K tokensFITS · 34.1 GB FREE
cache 0.9 GB
32K tokensFITS · 31.2 GB FREE
cache 3.8 GB
Which Macs run this
| Chip | Smallest RAM that fits | Speed est. |
|---|---|---|
| M1 | 8 GB | 14.4 tok/s |
| M1 Pro | 16 GB | 44.7 tok/s |
| M1 Max | 32 GB | 92.9 tok/s |
| M1 Ultra | 64 GB | 191 tok/s |
| M2 | 8 GB | 21.5 tok/s |
| M2 Pro | 16 GB | 45.3 tok/s |
| M2 Max | 32 GB | 94.1 tok/s |
| M2 Ultra | 64 GB | 193 tok/s |
| M3 | 8 GB | 21.5 tok/s |
| M3 Pro | 18 GB | 33.1 tok/s |
| M3 Max (14-core CPU) | 36 GB | 68.8 tok/s |
| M3 Max (16-core CPU) | 48 GB | 94.1 tok/s |
| M3 Ultra | 96 GB | 200 tok/s |
| M4 | 16 GB | 26.1 tok/s |
| M4 Pro | 24 GB | 62.6 tok/s |
| M4 Max (14-core CPU) | 36 GB | 97.7 tok/s |
| M4 Max (16-core CPU) | 48 GB | 132 tok/s |
| M5 | 16 GB | 33.8 tok/s |
| M5 Prounverified | 24 GB | 71.3 tok/s |
| M5 Maxunverified | 36 GB | 150 tok/s |