Local LLM model page

SmallThinker (3B)

Small reasoning model on Qwen 2.5 3B. Thinking at a tiny size. 83K downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
3B
Minimum RAM
4 GB
Model size
1.8 GB
Quantization
Q5_K_M

Can SmallThinker (3B) run locally?

SmallThinker (3B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q5_K_M as the default quantization, with at least 4 GB RAM.

Search term for LM Studio or compatible runtimes: smallthinker-3b-preview

Hugging Face repository: PowerInfer/SmallThinker-3B-Preview-GGUF

reasoninglightspeed

Strengths

  • Small reasoning model on Qwen 2.5 3B. Thinking at a tiny size. 83K downloads.

Limitations

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

Best use cases

  • reasoning
  • light
  • speed

Benchmarks

Speed: 9/10

Quality: 5/10

Coding: 4/10

Reasoning: 7/10

Technical details

Developer: smallthinker

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2025-01