What are the hardware requirements for Step 3.5 Flash Bf16?

Step 3.5 Flash Bf16 requires approximately 138.5 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Step 3.5 Flash Bf16 and how large is it?

Step 3.5 Flash Bf16 is developed by mlx-community, a model with 197b 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 3.5 Flash Bf16?

Step 3.5 Flash Bf16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Step 3.5 Flash Bf16 by mlx-community — VRAM 138.5GB, 256K context

Name: Step 3.5 Flash Bf16
Author: mlx-community

Step 3.5 Flash Bf16 is an open-source language model by mlx-community. Features: 197b LLM, VRAM: 138.5GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.23.

Base model:finetune:stepfun-ai... Base model:stepfun-ai/step-3.5... Conversational Custom code Mlx Region:us Safetensors Sharded Step3p5 Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Step-3.5-Flash-bf16

Step 3.5 Flash Bf16 Parameters and Internals

LLM Name	Step 3.5 Flash Bf16
Repository 🤗	https://huggingface.co/mlx-community/Step-3.5-Flash-bf16
Base Model(s)	stepfun-ai/Step-3.5-Flash stepfun-ai/Step-3.5-Flash
Model Size	197b
Required VRAM	138.5 GB
Updated	2026-08-10
Maintainer	mlx-community
Model Type	step3p5
Model Files	2.7 GB: 1-of-127 3.0 GB: 2-of-127 3.0 GB: 3-of-127 3.2 GB: 4-of-127 3.0 GB: 5-of-127 3.0 GB: 6-of-127 3.3 GB: 7-of-127 3.0 GB: 8-of-127 3.0 GB: 9-of-127 3.3 GB: 10-of-127 3.0 GB: 11-of-127 3.0 GB: 12-of-127 3.3 GB: 13-of-127 3.0 GB: 14-of-127 3.0 GB: 15-of-127 3.2 GB: 16-of-127 3.0 GB: 17-of-127 3.0 GB: 18-of-127 3.3 GB: 19-of-127 3.0 GB: 20-of-127 3.0 GB: 21-of-127 3.3 GB: 22-of-127 3.0 GB: 23-of-127 3.0 GB: 24-of-127 3.3 GB: 25-of-127 3.0 GB: 26-of-127 3.0 GB: 27-of-127 3.2 GB: 28-of-127 3.0 GB: 29-of-127 3.0 GB: 30-of-127 3.3 GB: 31-of-127 3.0 GB: 32-of-127 3.0 GB: 33-of-127 3.3 GB: 34-of-127 3.0 GB: 35-of-127 3.0 GB: 36-of-127 3.3 GB: 37-of-127 3.0 GB: 38-of-127 3.0 GB: 39-of-127 3.2 GB: 40-of-127 3.0 GB: 41-of-127 3.0 GB: 42-of-127 3.3 GB: 43-of-127 3.0 GB: 44-of-127 3.0 GB: 45-of-127
Model Architecture	Step3p5ForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Vocabulary Size	128896
Torch Data Type	bfloat16

Rank the Step 3.5 Flash Bf16 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 3.5 Flash Bf16

Best Alternatives	Context / RAM	Downloads	Likes
Step 3.5 Flash 8bit	256K / 210.7 GB	263	2
Step 3.5 Flash 4bit	256K / 110.3 GB	1164	10

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Step-3.5-Flash-bf16.