Meta AI · mllama
Can I run llama3.2-vision?
Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
Parameter counts and memory belong to each build below. A family can contain several sizes and tasks; fitting in memory is not a quality ranking.
Calculate memory for a build and contextllama3.2-vision system requirements
Memory needed at 4K context, counting model weights, KV cache, compute buffers and runtime overhead. Download sizes come from the official Ollama registry.
| Build | Quantization | Download | Memory needed |
|---|---|---|---|
| llama3.2-vision:11b11B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 7.3 GB | ~8.9 GB |
| llama3.2-vision:11b-instruct-q8_011B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q8_0 | 11.4 GB | ~13.4 GB |
| llama3.2-vision:11b-instruct-fp1611B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | F16 | 20.0 GB | ~22.6 GB |
| llama3.2-vision:90b90B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 50.9 GB | ~56.9 GB |
| llama3.2-vision:90b-instruct-q8_090B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q8_0 | 88.6 GB | ~97.6 GB |
| llama3.2-vision:90b-instruct-fp1690B parameters (tag)128K documented maximum contextBuild sourceCatalog checked 2026-10-13 | F16 | 165.2 GB | ~180.3 GB |
Showing the 6 smallest non-alias builds. Choose any build and change the context. A context above the build's documented maximum is a hypothetical calculation, not a supported setting.
How to run llama3.2-vision locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull llama3.2-vision:11b - 3.Check the source for the build's task. For text generation, run
ollama run llama3.2-vision:11b. Base/text builds may need a prompt template; an instruct build is usually the appropriate starting point for a conversation.
Frequently asked questions about llama3.2-vision
- How much VRAM do I need to run llama3.2-vision?
- At 4K context, the smallest published build of llama3.2-vision (Q4_K_M) needs roughly 8.9 GB of GPU memory once weights, KV cache, compute buffers and runtime overhead are counted. Bigger quantizations and longer context windows need more. It can also run partly or entirely on the CPU using system RAM, more slowly.
- Can I run llama3.2-vision without a dedicated GPU?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 8.9 GB at 4K context, plus headroom for your operating system. Check the build's runtime requirements. We have not measured its speed on your CPU.
- How big is the llama3.2-vision download?
- The smallest published build is 7.3 GB. There are 6 builds in total, the largest being 165.2 GB. Leave some extra free disk space beyond the download itself.
- How do I run llama3.2-vision locally?
- Install Ollama, then download a specific build with "ollama pull llama3.2-vision:11b". For a build that supports text generation, use ollama run with the same tag. Check the model source for its task and prompt format.
Will llama3.2-vision run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Compare with similar models
Or start from your memory: 8 GB VRAM, 12 GB VRAM, 16 GB VRAM, 24 GB VRAM or a 16 GB Mac.
Model data from the official Ollama registry · verified 13/10/2026