4-bit Open on Hugging Face
Parameters
3.1B
Weights (est.)
≈ 1.7 GB
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/smallthinker-3b-preview-q4 --prompt "Hello"
Details
- Base model
- Tiiny/SmallThinker-3B-Preview (quantized)
- Vendor
- Tiiny
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 45 in the last 30 days · 575 all time · 0 likes
- Published
- 2025-01-05 · updated 2025-01-05 (1y ago)
- Languages
- en
- Tags
- qwen2
Other MLX builds of Tiiny/SmallThinker-3B-Preview
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| smallthinker-3b-preview-q4 (this one) | 4-bit | ≈ 1.7 GB | 8 GB+ | 45 |
| SmallThinker-3B-Preview-4bit | 4-bit | ≈ 1.7 GB | 8 GB+ | 28 |
| SmallThinker-3B-Preview-6bit | 6-bit | ≈ 2.5 GB | 8 GB+ | 34 |
| smallthinker-3b-preview-q8 | 8-bit | ≈ 3.3 GB | 8 GB+ | 44 |