RunLocalAI
llama
90B parameters
Commercial OK
Multimodal

Llama 3.2 90B Vision Instruct

The 90B vision Llama. Best-in-class first-party multimodal open weight at the time of release. Workstation-class only.

License: Llama 3.2 Community License·Released Sep 25, 2024·Context: 131,072 tokens

Overview

The 90B vision Llama. Best-in-class first-party multimodal open weight at the time of release. Workstation-class only.

Strengths

  • Top-tier open-weight vision quality
  • 128K context

Weaknesses

  • Needs 60GB+ VRAM
  • EU restricted

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M51.0 GB60 GB

Get the model

Ollama

One-line install

ollama run llama3.2-vision:90bRead our Ollama review →

HuggingFace

Original weights

huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of Llama 3.2 90B Vision Instruct.

NVIDIA GB200 NVL72
13824GB · nvidia
AMD Instinct MI355X
288GB · amd
AMD Instinct MI325X
256GB · amd
AMD Instinct MI300X
192GB · amd
NVIDIA B200
192GB · nvidia
NVIDIA H100 NVL
188GB · nvidia
NVIDIA H200
141GB · nvidia
AMD Instinct MI250X
128GB · amd
Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Step down
Smaller — faster, runs on weaker hardware

Frequently asked

What's the minimum VRAM to run Llama 3.2 90B Vision Instruct?

60GB of VRAM is enough to run Llama 3.2 90B Vision Instruct at the Q4_K_M quantization (file size 51.0 GB). Higher-quality quantizations need more.

Can I use Llama 3.2 90B Vision Instruct commercially?

Yes — Llama 3.2 90B Vision Instruct ships under the Llama 3.2 Community License, which permits commercial use. Always read the license text before deployment.

What's the context length of Llama 3.2 90B Vision Instruct?

Llama 3.2 90B Vision Instruct supports a context window of 131,072 tokens (about 131K).

How do I install Llama 3.2 90B Vision Instruct with Ollama?

Run `ollama pull llama3.2-vision:90b` to download, then `ollama run llama3.2-vision:90b` to start a chat session. The default quantization is Q4_K_M.

Does Llama 3.2 90B Vision Instruct support images?

Yes — Llama 3.2 90B Vision Instruct is multimodal and accepts text + vision inputs. Vision support requires a runner that handles its image-conditioning architecture.

Source: huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.