Local LLM model page

LLaVA-Llama3 (8B)

LLaVA fine-tuned on Llama 3. Improved vision understanding. 1.9M downloads.

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

Can LLaVA-Llama3 (8B) run locally?

LLaVA-Llama3 (8B) 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: llava-llama-3-8b

Hugging Face repository: xtuner/llava-llama-3-8b-v1_1-GGUF

visionstandard

Strengths

  • LLaVA fine-tuned on Llama 3. Improved vision understanding. 1.9M downloads.

Limitations

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

Best use cases

  • vision
  • standard

Benchmarks

Speed: 7/10

Quality: 7/10

Coding: 4/10

Reasoning: 6/10

Technical details

Developer: llava

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-04