Will this model run on your hardware?
Can I run StepFun: Step 5 Preview locally?
- 604B parameters (43B active, MoE)
- context up to 1024K
- licence: other
- #40 in the AIContenders model ranking
- Weights: stepfun-ai/Step-5-Preview · GGUF: smalinin/Step-5-Preview-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 |
|---|---|
| Q2_K | 182.5 GB |
Run it locally
ollama run hf.co/smalinin/Step-5-Preview-GGUF:Q2_K
llama serve -hf smalinin/Step-5-Preview-GGUF:Q2_K
LM Studio: open smalinin/Step-5-Preview-GGUF