Step 3.5 Flash
Step 3.5 Flash is an open-weights language model from StepFun, released January 29, 2026. It has 199B parameters (dense). The context window is 250K tokens. API price: $0.1 input / $0.31 output per million tokens.
Check it against your own PC →
Can you run Step 3.5 Flash locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Too large | – | – | – | – |
Ready-made quantizations on Hugging Face: ggml-org/Step-3.5-Flash-GGUF · bartowski/stepfun-ai_Step-3.5-Flash-GGUF · mudler/Step-3.5-Flash-APEX-GGUF · mradermacher/Step-3.5-Flash-i1-GGUF · mradermacher/Step-3.5-Flash-GGUF · ubergarm/Step-3.5-Flash-GGUF
Benchmark results
Epoch AI has not published results for Step 3.5 Flash yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: stepfun-ai/Step-3.5-Flash