4-bit Open on Hugging Face
Parameters
33B
Weights (est.)
≈ 18.4 GB
Mac memory (est.)
24 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/simplescaling-s1-32B-4bit --prompt "Hello"
Details
- Base model
- simplescaling/s1-32B (quantized)
- Vendor
- simplescaling
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 40 in the last 30 days · 247 all time · 1 likes
- Published
- 2025-02-11 · updated 2025-02-11 (1y ago)
- Tags
- qwen2
Other MLX builds of simplescaling/s1-32B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| simplescaling-s1-32B-4bit (this one) | 4-bit | ≈ 18.4 GB | 24 GB+ | 40 |
| simplescaling-s1-32B-8bit | 8-bit | ≈ 34.8 GB | 48 GB+ | 31 |
| simplescaling-s1-32B-fp16 | fp16 | ≈ 65.5 GB | 96 GB+ | 34 |
| simplescaling-s1-32B-bf16 | bf16 | ≈ 65.5 GB | 96 GB+ | 28 |
| simplescaling-s1-32B-fp32 | fp32 | ≈ 131 GB | 192 GB+ | 44 |