3-bit Open on Hugging Face
Parameters
1.7B
Weights (est.)
≈ 753 MB
Mac memory (est.)
8 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/Qwen3-1.7B-3bit --prompt "Hello"
Details
- Base model
- Qwen/Qwen3-1.7B (quantized)
- Vendor
- Qwen
- Task
- Text generation
- Quantisation
- 3-bit
- Licence
- apache-2.0
- Downloads
- 88 in the last 30 days · 884 all time · 0 likes
- Published
- 2025-04-28 · updated 2025-04-28 (1y ago)
- Tags
- qwen3
Other MLX builds of Qwen/Qwen3-1.7B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3-1.7B-3bit (this one) | 3-bit | ≈ 753 MB | 8 GB+ | 88 |
| Qwen3-1.7B-4bit | 4-bit | ≈ 968 MB | 8 GB+ | 16K |
| Qwen3-1.7B-4bit-DWQ-053125 | 4-bit DWQ | ≈ 968 MB | 8 GB+ | 812 |
| Qwen3-1.7B-4bit-DWQ | 4-bit DWQ | ≈ 968 MB | 8 GB+ | 296 |
| Qwen3-1.7B-MLX-MXFP4 | MXFP4 | ≈ 968 MB | 8 GB+ | 82 |
| Qwen3-1.7B-4bit-AWQ | 4-bit | ≈ 968 MB | 8 GB+ | 79 |
| Qwen3-1.7B-5bit | 5-bit | ≈ 1.2 GB | 8 GB+ | 73 |
| Qwen3-1.7B-6bit | 6-bit | ≈ 1.4 GB | 8 GB+ | 106 |
| Qwen3-1.7B-8bit | 8-bit | ≈ 1.8 GB | 8 GB+ | 758 |
| Qwen3-1.7B-bf16 | bf16 | ≈ 3.4 GB | 8 GB+ | 663 |