4-bit Open on Hugging Face
Parameters
596M
Weights (est.)
≈ 335 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/S1-mini-MLX-4bit --prompt "Hello"
Details
- Base model
- superwhisper/s1-mini (quantized)
- Vendor
- superwhisper
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- s1-mini-license
- Downloads
- 785 in the last 30 days · 2.8K all time · 0 likes
- Published
- 2026-08-20 · updated 2026-08-20 (2mo ago)
- Languages
- en
- Tags
- qwen3, text-normalization, inverse-text-normalization, punctuation, truecasing, speech-to-text, dictation, post-processing
Other MLX builds of superwhisper/s1-mini
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| S1-mini-MLX-4bit (this one) | 4-bit | ≈ 335 MB | 8 GB+ | 785 |
| S1-mini-MLX-8bit | 8-bit | ≈ 633 MB | 8 GB+ | 129 |
| S1-mini-MLX-bf16 | bf16 | ≈ 1.2 GB | 8 GB+ | 92 |