Local LLM model page

LLaVA 1.6 (7B)

The original multimodal hero. Drag & drop images into LM Studio to discuss them.

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

Can LLaVA 1.6 (7B) run locally?

LLaVA 1.6 (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: llava-v1.6-mistral-7b

Hugging Face repository: lmstudio-community/llava-v1.6-mistral-7b-GGUF

visionstandard

Strengths

  • The original multimodal hero. Drag & drop images into LM Studio to discuss them.

Limitations

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

Best use cases

  • vision
  • standard

Benchmarks

Speed: 7/10

Quality: 6/10

Coding: 3/10

Reasoning: 5/10

Technical details

Developer: llava

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-02