Model · Meta · Vision
Llama 3.2 Vision
Meta's open-weight vision-language family. 11B and 90B variants — the practical open-weights vision model for self-hosted multimodal applications.
- Modality
- Vision
- License
- Llama 3.2 Community License (Open weights)
- Parameter size
- 11B / 90B
- Context window
- 128,000 tokens
- Released
- September 25, 2024
- Last verified
- June 8, 2026
- Runs locally
- Yes
- Also handles
- text
What you need to run it
- Mac
- Yes. Any Apple Silicon Mac (M1 or newer) with at least 16 GB (24 GB recommended) of memory. Newer chips are faster, but memory is what decides whether it runs.
- Windows / Linux PC
- NVIDIA works best. A graphics card with at least 12 GB (16 GB recommended) of video memory.
- No graphics card
- Not practical. Too slow without a graphics card or Apple Silicon.
Ollama runs the 11B on a Mac; the 90B version (about 55 GB) needs a 64 GB or larger Mac.
Numbers are for: 4-bit build of the 11B (about 8 GB). Our estimate from the model’s size — the maker publishes no figure.
Strengths
- Open weights — runs offline on capable hardware
- Two sizes for different hardware budgets
- Inherits Llama 3 ecosystem support
Weaknesses
- Not available in EU region under the Community License
- 11B variant trades quality for tractability
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face | weights | Gated — accept Community License |
| OpenRouter | hosted-api | API key required |
| Ollama | local | ollama run llama3.2-vision |
Used in solutions
Version history
- Llama 3.3 70B Dec 2024
- Llama 3.2 Vision Sep 2024 Current
- Llama 3.1 8B Jul 2024
Official sources
- Model card model
Change log
- — Added hardware requirements (Mac support, memory, NVIDIA). Source: estimate from size; Ollama llama3.2-vision page; mlx-community Llama-3.2-11B-Vision-Instruct-4bit.
- — Initial entry.
Esc