Local LLM model page

LLaVA-Phi3 (3.8B)

Small LLaVA on Phi 3. Vision understanding at ultra-compact size. 126K 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 LLaVA-Phi3 (3.8B) run locally?

LLaVA-Phi3 (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: llava-phi-3-mini

Hugging Face repository: xtuner/llava-phi-3-mini-GGUF

visionlightspeed

Strengths

  • Small LLaVA on Phi 3. Vision understanding at ultra-compact size. 126K downloads.

Limitations

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

Best use cases

  • vision
  • light
  • speed

Benchmarks

Speed: 9/10

Quality: 5/10

Coding: 3/10

Reasoning: 5/10

Technical details

Developer: llava

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-05