Step 3.5 Flash 8bit by mlx-community

 »  All LLMs  »  mlx-community  »  Step 3.5 Flash 8bit   URL Share it on

Step 3.5 Flash 8bit is an open-source language model by mlx-community. Features: 197b LLM, VRAM: 210.7GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.28.

  8-bit   8bit Base model:quantized:stepfun-a... Base model:stepfun-ai/step-3.5...   Conversational   Custom code   Mlx   Quantized   Region:us   Safetensors   Sharded   Step3p5   Tensorflow

Step 3.5 Flash 8bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Step 3.5 Flash 8bit Parameters and Internals

LLM NameStep 3.5 Flash 8bit
Repository 🤗https://huggingface.co/mlx-community/Step-3.5-Flash-8bit 
Base Model(s)  stepfun-ai/Step-3.5-Flash   stepfun-ai/Step-3.5-Flash
Model Size197b
Required VRAM210.7 GB
Updated2026-04-08
Maintainermlx-community
Model Typestep3p5
Model Files  4.6 GB: 1-of-43   4.9 GB: 2-of-43   5.0 GB: 3-of-43   5.0 GB: 4-of-43   5.0 GB: 5-of-43   4.9 GB: 6-of-43   5.0 GB: 7-of-43   5.0 GB: 8-of-43   5.0 GB: 9-of-43   4.9 GB: 10-of-43   5.0 GB: 11-of-43   5.0 GB: 12-of-43   5.0 GB: 13-of-43   4.9 GB: 14-of-43   5.0 GB: 15-of-43   5.0 GB: 16-of-43   5.0 GB: 17-of-43   4.9 GB: 18-of-43   5.0 GB: 19-of-43   5.0 GB: 20-of-43   5.0 GB: 21-of-43   4.9 GB: 22-of-43   5.0 GB: 23-of-43   5.0 GB: 24-of-43   5.0 GB: 25-of-43   4.9 GB: 26-of-43   5.0 GB: 27-of-43   5.0 GB: 28-of-43   5.0 GB: 29-of-43   4.9 GB: 30-of-43   5.0 GB: 31-of-43   5.0 GB: 32-of-43   5.0 GB: 33-of-43   4.9 GB: 34-of-43   5.0 GB: 35-of-43   5.0 GB: 36-of-43   5.0 GB: 37-of-43   4.9 GB: 38-of-43   5.0 GB: 39-of-43   5.0 GB: 40-of-43   5.0 GB: 41-of-43   4.9 GB: 42-of-43   2.2 GB: 43-of-43
Quantization Type8bit
Model ArchitectureStep3p5ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Vocabulary Size128896
Torch Data Typebfloat16

Best Alternatives to Step 3.5 Flash 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Step 3.5 Flash 4bit256K / 110.3 GB28698
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Step-3.5-Flash-8bit.

Rank the Step 3.5 Flash 8bit Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 53640 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a