4-bit Open on Hugging Face
Parameters
197B
Weights (est.)
≈ 111 GB
Mac memory (est.)
128 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/Step-3.5-Flash-4bit --prompt "Hello"
Details
- Base model
- stepfun-ai/Step-3.5-Flash (quantized)
- Vendor
- stepfun-ai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 405 in the last 30 days · 15K all time · 10 likes
- Published
- 2026-02-02 · updated 2026-02-04 (9mo ago)
- Tags
- step3p5, custom_code
Other MLX builds of stepfun-ai/Step-3.5-Flash
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Step-3.5-Flash-4bit (this one) | 4-bit | ≈ 111 GB | 128 GB+ | 405 |
| Step-3.5-Flash-6bit | 6-bit | ≈ 160 GB | 192 GB+ | 88 |
| Step-3.5-Flash-8bit | 8-bit | ≈ 209 GB | 256 GB+ | 93 |
| Step-3.5-Flash-bf16 | bf16 | ≈ 394 GB | 512 GB+ | 29 |