Local LLM model page

Bespoke MiniCheck (3.8B)

Fact-checking specialist model. Verify claims and detect hallucinations. 44K downloads.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
3.8B
Minimum RAM
6 GB
Model size
2.3 GB
Quantization
Q5_K_M

Can Bespoke MiniCheck (3.8B) run locally?

Bespoke MiniCheck (3.8B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q5_K_M as the default quantization, with at least 6 GB RAM.

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

Hugging Face repository: bespokelabs/Bespoke-MiniCheck-7B-GGUF

lightspeed

Strengths

  • Fact-checking specialist model. Verify claims and detect hallucinations. 44K downloads.

Limitations

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

Best use cases

  • light
  • speed

Benchmarks

Speed: 9/10

Quality: 5/10

Coding: 2/10

Reasoning: 6/10

Technical details

Developer: bespoke

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-10