Local LLM model page

OpenThinker (7B)

Open reasoning model distilled from DeepSeek R1. Excellent chain-of-thought. 601K downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
7B
Minimum RAM
8 GB
Model size
4.5 GB
Quantization
Q4_K_M

Can OpenThinker (7B) run locally?

OpenThinker (7B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q4_K_M as the default quantization, with at least 8 GB RAM.

Search term for LM Studio or compatible runtimes: openthinker-7b

Hugging Face repository: open-thoughts/OpenThinker-7B-GGUF

reasoningstandard

Strengths

  • Open reasoning model distilled from DeepSeek R1. Excellent chain-of-thought. 601K downloads.

Limitations

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

Best use cases

  • reasoning
  • standard

Benchmarks

Speed: 8/10

Quality: 7/10

Coding: 6/10

Reasoning: 8/10

Technical details

Developer: openthinker

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2025-02