Will this model run on your hardware?
Can I run StepFun: Step 3.7 Flash locally?
- 201B parameters
- context up to 256K
- licence: apache-2.0
- Weights: stepfun-ai/Step-3.7-Flash · GGUF: unsloth/Step-3.7-Flash-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 209.4 GB |
| UD-Q6_K | 163.3 GB |
| UD-Q5_K_M | 146.5 GB |
| UD-Q4_K_M | 122.1 GB |
| MXFP4 | 118.3 GB |
| UD-Q3_K_M | 89.3 GB |
Run it locally
ollama run hf.co/unsloth/Step-3.7-Flash-GGUF:UD-Q4_K_M
llama serve -hf unsloth/Step-3.7-Flash-GGUF:UD-Q4_K_M
LM Studio: open unsloth/Step-3.7-Flash-GGUF