Local LLM model page

Step 3.5 Flash

StepFun's fast and free model. Exceptional speed-to-quality ratio. Popular in Asian markets. Ranks #9 on global usage leaderboards with 18.7B monthly tokens.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
14B
Minimum RAM
16 GB
Model size
9.5 GB
Quantization
Q4_K_M

Can Step 3.5 Flash run locally?

Step 3.5 Flash is best suited for mainstream Macs and PCs with 16 GB RAM. LocalClaw recommends Q4_K_M as the default quantization, with at least 16 GB RAM.

Search term for LM Studio or compatible runtimes: step-3.5-flash

Hugging Face repository: stepfun-ai/Step-3.5-Flash-GGUF

chatcodepowerspeed

Strengths

  • StepFun's fast and free model. Exceptional speed-to-quality ratio. Popular in Asian markets. Ranks #9 on global usage leaderboards with 18.7B monthly tokens.

Limitations

  • Performance depends heavily on quantization, RAM bandwidth and runtime support.

Best use cases

  • chat
  • code
  • power
  • speed

Benchmarks

Speed: 8/10

Quality: 7/10

Coding: 7/10

Reasoning: 7/10

Technical details

Developer: step

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2025-11