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/Sky-T1-32B-Preview-4bit --prompt "Hello"
Details
- Base model
- NovaSky-AI/Sky-T1-32B-Preview (quantized)
- Vendor
- NovaSky-AI
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 59 in the last 30 days · 1.4K all time · 0 likes
- Published
- 2025-01-13 · updated 2025-01-13 (1y ago)
- Languages
- en
- Tags
- qwen2
Other MLX builds of NovaSky-AI/Sky-T1-32B-Preview
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Sky-T1-32B-Preview-4bit (this one) | 4-bit | ≈ 18.4 GB | 24 GB+ | 59 |
| Sky-T1-32B-Preview-8bit | 8-bit | ≈ 34.8 GB | 48 GB+ | 43 |
| Sky-T1-32B-Preview | — | ≈ 65.5 GB | 96 GB+ | 55 |