Local LLM model page

Llama 3.2 Vision (90B)

Meta's largest vision model. 128K context with powerful image reasoning and analysis. Requires significant hardware.

Find the best model for my hardwareBrowse all 183 LLMs
Parameters
90B
Minimum RAM
72 GB
Model size
55 GB
Quantization
Q4_K_M

Can Llama 3.2 Vision (90B) run locally?

Llama 3.2 Vision (90B) is best suited for large-memory workstations. LocalClaw recommends Q4_K_M as the default quantization, with at least 72 GB RAM.

Search term for LM Studio or compatible runtimes: llama-3.2-90b-vision-instruct

Hugging Face repository: meta-llama/Llama-3.2-90B-Vision-Instruct-GGUF

visionquality

Strengths

  • Meta's largest vision model. 128K context with powerful image reasoning and analysis. Requires significant hardware.

Limitations

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

Best use cases

  • vision
  • quality

Benchmarks

Speed: 1/10

Quality: 10/10

Coding: 7/10

Reasoning: 9/10

Technical details

Developer: llama

License: See model repository

Context window: Unknown tokens

Architecture: See model card

Released: 2024-09