simplescaling-s1.1-32B-6bit
mlx-community/simplescaling-s1.1-32B-6bit
Text generation · transformers
6-bit Open on Hugging Face
Parameters
33B
Weights (est.)
≈ 26.6 GB
Mac memory (est.)
32 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-s1.1-32B-6bit --prompt "Hello"
Details
- Base model
- simplescaling/s1.1-32B (quantized)
- Vendor
- simplescaling
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- apache-2.0
- Downloads
- 24 in the last 30 days · 173 all time · 0 likes
- Published
- 2025-02-12 · updated 2025-02-16 (1y ago)
- Tags
- qwen2
Other MLX builds of simplescaling/s1.1-32B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| s1.1-32B-4bit | 4-bit | ≈ 1000 MB | 8 GB+ | 20 |
| simplescaling-s1.1-32B-4bit | 4-bit | ≈ 18.4 GB | 24 GB+ | 29 |
| simplescaling-s1.1-32B-6bit (this one) | 6-bit | ≈ 26.6 GB | 32 GB+ | 24 |
| simplescaling-s1.1-32B-8bit | 8-bit | ≈ 34.8 GB | 48 GB+ | 35 |
| simplescaling-s1.1-32B-fp16 | fp16 | ≈ 65.5 GB | 96 GB+ | 23 |
| simplescaling-s1.1-32B-fp32 | fp32 | ≈ 131 GB | 192 GB+ | 42 |