2-bit Open on Hugging Face
Parameters
199B
Weights (est.)
≈ 62.6 GB
Mac memory (est.)
96 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-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/Step-3.7-Flash-oQ2e --image photo.jpg --prompt "Describe this image"
Details
- Base model
- stepfun-ai/Step-3.7-Flash (quantized)
- Vendor
- stepfun-ai
- Task
- Vision + text
- Quantisation
- 2-bit
- Licence
- apache-2.0
- Downloads
- 49 in the last 30 days · 565 all time · 0 likes
- Published
- 2026-07-18 · updated 2026-07-19 (3mo ago)
- Tags
- step3p7, quantized, custom_code
Other MLX builds of stepfun-ai/Step-3.7-Flash
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Step-3.7-Flash-oQ2e (this one) | 2-bit | ≈ 62.6 GB | 96 GB+ | 49 |
| Step-3.7-Flash-oQ3e | 3-bit | ≈ 87.5 GB | 128 GB+ | 58 |
| Step-3.7-Flash-4bit | 4-bit | ≈ 111 GB | 128 GB+ | 143 |
| Step-3.7-Flash-6bit | 6-bit | ≈ 160 GB | 192 GB+ | 26 |
| Step-3.7-Flash-8bit | 8-bit | ≈ 209 GB | 256 GB+ | 39 |