Local LLM model page

Llama 3 (8B)

Meta Llama 3 original. Rock-solid foundation model. 11.2M downloads. Widely supported and fine-tuned.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
8B
Minimum RAM
8 GB
Model size
4.7 GB
Quantization
Q5_K_M

Can Llama 3 (8B) run locally?

Llama 3 (8B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q5_K_M as the default quantization, with at least 8 GB RAM.

Search term for LM Studio or compatible runtimes: llama-3-8b-instruct

Hugging Face repository: lmstudio-community/Meta-Llama-3-8B-Instruct-GGUF

chatcodestandardgeneral

Strengths

  • 11.2M downloads — industry standard
  • Rock-solid foundation
  • Massive fine-tune ecosystem

Limitations

  • Only 8K context
  • English-only
  • Superseded by 3.1 and 3.3

Best use cases

  • General chat
  • Fine-tuning base
  • Text generation

Benchmarks

Speed: 8/10

Quality: 7/10

Coding: 7/10

Reasoning: 6/10

Technical details

Developer: Meta AI

License: Llama 3 Community License

Context window: 8,192 tokens

Architecture: Transformer decoder-only with GQA

Released: 2024-04

Similar models

llama3.1-8bgemma2-9bmistral-7b