- Size
- 201B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
- On the Hub since
- 23 May 2026the date the repo was created
- Context length
- 256k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Step3p7ForConditionalGeneration
- On Hugging Face
- stepfun-ai/Step-3.7-Flash9.6k downloads in the last 30 days, 463 likes
Scores
- default setting2.3%via Epoch AI
Epoch's name: step-3.7-flash. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 3.6 GB, worked out from the model's config (stepfun-ai/Step-3.7-Flash), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
stepfun-ai/Step-3.7-Flash-GGUF (the maker's own conversion), 3.7k downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-step3.7-flash-f16.gguf (3.7 GB), not counted below.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XXS | 70.6 GBfile size, 2 parts | 74.6 GB70.6 + 3.6 + 0.50 | Commandsllama.cpp llama-server -hf stepfun-ai/Step-3.7-Flash-GGUF:IQ3_XXSDownload hf download stepfun-ai/Step-3.7-Flash-GGUF --include "IQ3_XXS/Step-3.7-flash-IQ3_XXS-*-of-00002.gguf" --local-dir Step-3.7-Flash-GGUF |
| Q3_K_M | 87.4 GBfile size, 3 parts | 91.4 GB87.4 + 3.6 + 0.50 | Commandsllama.cpp llama-server -hf stepfun-ai/Step-3.7-Flash-GGUF:Q3_K_MDownload hf download stepfun-ai/Step-3.7-Flash-GGUF --include "Q3_K_M/Step-3.7-flash-Q3_K_M-*-of-00003.gguf" --local-dir Step-3.7-Flash-GGUF |
| Q3_K_L | 95.5 GBfile size, 3 parts | 99.5 GB95.5 + 3.6 + 0.50 | Commandsllama.cpp llama-server -hf stepfun-ai/Step-3.7-Flash-GGUF:Q3_K_LDownload hf download stepfun-ai/Step-3.7-Flash-GGUF --include "Q3_K_L/Step-3.7-flash-Q3_K_L-*-of-00003.gguf" --local-dir Step-3.7-Flash-GGUF |
| IQ4_XS | 97.8 GBfile size, 3 parts | 101.8 GB97.8 + 3.6 + 0.50 | Commandsllama.cpp llama-server -hf stepfun-ai/Step-3.7-Flash-GGUF:IQ4_XSDownload hf download stepfun-ai/Step-3.7-Flash-GGUF --include "IQ4_XS/Step-3.7-flash-IQ4_XS-*-of-00003.gguf" --local-dir Step-3.7-Flash-GGUF |
| Q4_K_S | 103.8 GBfile size, 3 parts | 107.9 GB103.8 + 3.6 + 0.50 | Commandsllama.cpp llama-server -hf stepfun-ai/Step-3.7-Flash-GGUF:Q4_K_SDownload hf download stepfun-ai/Step-3.7-Flash-GGUF --include "Q4_K_S/Step-3.7-flash-Q4_K_S-*-of-00003.gguf" --local-dir Step-3.7-Flash-GGUF |
| Q8_0 | 195.0 GBfile size, 5 parts | 199.1 GB195.0 + 3.6 + 0.50 | Commandsllama.cpp llama-server -hf stepfun-ai/Step-3.7-Flash-GGUF:Q8_0Download hf download stepfun-ai/Step-3.7-Flash-GGUF --include "Q8_0/Step-3.7-flash-Q8_0-*-of-00005.gguf" --local-dir Step-3.7-Flash-GGUF |
| BF16 | 367.0 GBfile size, 9 parts | 371.0 GB367.0 + 3.6 + 0.50 | Commandsllama.cpp llama-server -hf stepfun-ai/Step-3.7-Flash-GGUF:BF16Download hf download stepfun-ai/Step-3.7-Flash-GGUF --include "BF16/Step3.7-flash-bf16-*-of-00009.gguf" --local-dir Step-3.7-Flash-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLXlemuralabs/Step-3.7-Flash-OptiQ-3.7bpw-mlx | 99.1 GBfile size | 103.1 GB99.1 + 3.6 + 0.50 | Download page |
| MLX 4bitmlx-community/Step-3.7-Flash-4bit | 103.2 GBfile size | 107.3 GB103.2 + 3.6 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 375.1 GBfile size | 379.1 GB375.1 + 3.6 + 0.50 |
hf download stepfun-ai/Step-3.7-Flash --local-dir Step-3.7-FlashOther conversions (7; sizes not read)
- stepfun-ai/Step-3.7-Flash-FP8 FP8, by the maker, 3.0k downloads
- stepfun-ai/Step-3.7-Flash-NVFP4 NVFP4, by the maker, 2.1k downloads
- AxionML/Step-3.7-Flash-NVFP4 NVFP4, 163 downloads
- cyankiwi/Step-3.7-Flash-AWQ-INT4 AWQ, int4, 97 downloads
- olka-fi/Step-3.7-Flash-MXFP4 Other, mxfp4, 34 downloads
- turboderp/Step-3.7-Flash-exl3 EXL3, 31 downloads
- tcclaviger/Step-3.7-Flash-240REAP-MXFP416 Other, 25 downloads
The Hub tags 40 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
4 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.
| Provider | In | Out | Context | Precision | Tokens/s | First token | Uptime 24h | Tools | JSON |
|---|---|---|---|---|---|---|---|---|---|
| deepinfra | $0.20 | $1.15 | 256k | not given | 27 | 0.6 s | ? | yes | yes |
| Novita | $0.20 | $1.15 | 256k | fp8 | 23 | 5.6 s | 100.0% | yes | yes |
| StepFun | $0.20 | $1.15 | 250k | fp8 | 105 | 3.8 s | 99.8% | yes | yes |
| featherless-ai | ? | ? | ? | not given | ? | ? | ? | not given | not given |
Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.
curl https://router.huggingface.co/v1/chat/completions \
-H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \
-d '{"model": "stepfun-ai/Step-3.7-Flash:deepinfra", "messages": [{"role": "user", "content": "Hello"}]}'Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.