LocalClaw/LLM/Llama 3.2 Vision (90B)
Open-weight local LLM

Llama 3.2 Vision (90B)

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

Large-memory workstation 72 GB RAM Q4_K_M Vision tasks
Run with LocalClaw Compare all models
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) needs a serious workstation with large unified memory or high VRAM.

Search for llama-3.2-90b-vision-instruct in LM Studio or another GGUF-compatible runtime.

meta-llama/Llama-3.2-90B-Vision-Instruct-GGUF
visionquality

Install path

01
Check RAM fitMinimum 72 GB RAM. Start with the Q4_K_M quant.
02
Load the modelSearch llama-3.2-90b-vision-instruct in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Strengths

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

Limitations

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

Best use cases

  • vision
  • quality

Capability profile

speed
1
quality
10
coding
7
reasoning
9

Technical notes

Developer
llama
License
See model repository
Context window
Unknown tokens
Architecture
See model card

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Large unified memoryMac Studio M4 Max 128GB128GB AI PC classNVIDIA GB10 / DGX SparkHigh-memory picks128GB RAM guide

Where to go next