# Step-3.7-Flash: official model and deployment card

Official Step 3.7 Flash card with serving examples and high-memory workstation options, including distinct engine paths.

- Type: Official model card
- Evidence: source_reported; site reproduced: false
- Model family: Step
- Model: stepfun-ai/Step-3.7-Flash
- Original author: stepfun-ai
- Original project: https://huggingface.co/stepfun-ai/Step-3.7-Flash
- Pinned document: https://huggingface.co/stepfun-ai/Step-3.7-Flash/blob/5f6244077ac62e04eec3f320501ff8c2b293373a/README.md
- Source revision: 5f6244077ac62e04eec3f320501ff8c2b293373a
- Source commit time (not experiment date): 2026-06-03T04:11:57.000Z
- Checked: 2026-10-17
- Experiment date: None
- Runtime topics: vLLM, SGLang, Transformers, llama.cpp
- Hardware topics: apple, amd, nvidia
- Reported setup: {"system": null, "node_count": null, "parallelism": null, "kv_dtype": null, "context_limit_tokens": null, "experiment_date": null}
- Performance figures: attributed selections with per-point conditions; no cross-source ranking

## Conditions

Unknown is null. Recipe options are not measured benchmark settings.

```json
{
  "conditions": {
    "model_revision": "5f6244077ac62e04eec3f320501ff8c2b293373a",
    "weight_hash": null,
    "runtime_execution_revision": null,
    "input_tokens": null,
    "output_tokens": null,
    "concurrency": null,
    "cache_state": null,
    "quantization": null,
    "speculative_decoding": null,
    "temperature": null,
    "top_p": null
  },
  "test_profiles": [],
  "recipe_parameters": null,
  "deployment_options": []
}
```

## Reading notes

- Local deployment sections distinguish vLLM, SGLang and Transformers.
- The card discusses high-memory Apple, AMD and NVIDIA workstation paths.

## Limits

- Hardware mentions are publisher guidance, not a Run AI Here compatibility test.

## License declaration

{"declared_spdx": "apache-2.0", "declared_name": null, "scope": "Publisher model-card declaration; inspect the linked LICENSE and artifact-specific terms."}


## Editorial answer

Official Step 3.7 Flash card with serving examples and high-memory workstation options, including distinct engine paths.

By Run AI Here editorial · 2026-10-17

AI-assisted source reading and original editorial synthesis; no independent model execution.

## What is included in Step 3.7 Flash?

The publisher describes about 198B parameters in total, combining a 196B language backbone and a 1.8B vision encoder, with roughly 11B active parameters per token. The advertised context is 256K tokens and reasoning has low, medium and high levels. These architecture labels do not establish a local memory budget.

Sources: https://huggingface.co/stepfun-ai/Step-3.7-Flash/blob/5f6244077ac62e04eec3f320501ff8c2b293373a/README.md#L17

## Is the advertised throughput a desktop benchmark?

The introduction advertises up to 400 tokens per second, but does not identify a matching local workstation configuration in that sentence. We do not reuse it as a measured Spark, Apple or consumer-GPU result. Its capability scores also name distinct tasks and tool settings, such as SimpleVQA with search and V* with Python.

Sources: https://huggingface.co/stepfun-ai/Step-3.7-Flash/blob/5f6244077ac62e04eec3f320501ff8c2b293373a/README.md#L17

## Which local engine paths are documented?

The card separates vLLM, SGLang, Transformers and llama.cpp paths. Transformers is presented as a debugging and verification route. The vLLM recipe has explicit precision and multi-GPU choices; the existence of a llama.cpp section does not mean a generic GGUF or an arbitrary runtime revision supports the model.

Sources: https://huggingface.co/stepfun-ai/Step-3.7-Flash/blob/5f6244077ac62e04eec3f320501ff8c2b293373a/README.md#L124

## What must be fixed before testing?

Choose the exact weight format, reasoning level, parser and engine version, then retain prompt/output lengths and cache policy. A vision request also needs its image preprocessing and encoder placement. Keep a short load check separate from a timed or quality evaluation, and attribute all figures here to the publisher until an independent run exists.

Sources: https://huggingface.co/stepfun-ai/Step-3.7-Flash/blob/5f6244077ac62e04eec3f320501ff8c2b293373a/README.md#L128

## Attributed configuration facts

```json
[
  {
    "name": "Total / language / vision / active parameters",
    "value": "198B / 196B / 1.8B / approximately 11B",
    "classification": "publisher_declaration",
    "evidence_url": "https://huggingface.co/stepfun-ai/Step-3.7-Flash/blob/5f6244077ac62e04eec3f320501ff8c2b293373a/README.md#L17",
    "source_document_sha256": "b0d04c993d40a28fff3ecac99045de502e75b0c0635e233f2aa8614783972519"
  },
  {
    "name": "Published context / reasoning levels",
    "value": "256K / low, medium, high",
    "classification": "publisher_declaration",
    "evidence_url": "https://huggingface.co/stepfun-ai/Step-3.7-Flash/blob/5f6244077ac62e04eec3f320501ff8c2b293373a/README.md#L17",
    "source_document_sha256": "b0d04c993d40a28fff3ecac99045de502e75b0c0635e233f2aa8614783972519"
  }
]
```