What are the hardware requirements for Step 3.7 Flash FP8?

Step 3.7 Flash FP8 requires approximately 0.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Step 3.7 Flash FP8 and how large is it?

Step 3.7 Flash FP8 is developed by stepfun-ai, a model with 201.4b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Step 3.7 Flash FP8?

Step 3.7 Flash FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Step 3.7 Flash FP8 by stepfun-ai — VRAM 0.9GB

Name: Step 3.7 Flash FP8
Author: stepfun-ai

Step 3.7 Flash FP8 is an open-source language model by stepfun-ai. Features: 201.4b LLM, VRAM: 0.9GB, License: apache-2.0, LLM Explorer Score: 0.31.

Conversational Custom code En Fp8 Image-text-to-text Moe Multimodal Region:us Safetensors Step3p7 Vision Vision-language

Model Card on HF 🤗: https://huggingface.co/stepfun-ai/Step-3.7-Flash-FP8

Step 3.7 Flash FP8 Parameters and Internals

LLM Name	Step 3.7 Flash FP8
Repository 🤗	https://huggingface.co/stepfun-ai/Step-3.7-Flash-FP8
Model Size	201.4b
Required VRAM	0.9 GB
Updated	2026-08-08
Maintainer	stepfun-ai
Model Type	step3p7
Model Files	0.9 GB 5.3 GB 9.5 GB 9.6 GB 9.5 GB 9.6 GB 9.5 GB 9.6 GB 9.5 GB 9.6 GB 9.5 GB 9.6 GB 9.5 GB 9.6 GB 9.5 GB 9.6 GB 9.5 GB 9.6 GB 9.5 GB 9.6 GB 9.5 GB 9.6 GB 4.7 GB 7.0 GB 1.6 GB 2.4 GB
Supported Languages	en
Model Architecture	Step3p7ForConditionalGeneration
License	apache-2.0
Model Max Length	131072
Tokenizer Class	LlamaTokenizerFast
Padding Token	<｜end▁of▁sentence｜>

Rank the Step 3.7 Flash FP8 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Step 3.7 Flash FP8

Best Alternatives	Context / RAM	Downloads	Likes
Step 3.7 Flash	256K / 0.9 GB	14	1
Step 3.7 Flash	0K / 0.9 GB	17965	228

Note: green Score (e.g. "73.2") means that the model is better than stepfun-ai/Step-3.7-Flash-FP8.