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.
10.7B parameters128K contextimagetext**Llama 3.2** **Acceptable Use Policy**6 builds
llama3.2-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:11b | Q4_K_M | 7.3 GB | ~10.8 GB(est.) |
| llama3.2-vision:11b-instruct-q8_0 | Q8_0 | 11.4 GB | ~16.7 GB(est.) |
| llama3.2-vision:11b-instruct-fp16 | F16 | 20.0 GB | ~29.0 GB(est.) |
| llama3.2-vision:90b | Q4_K_M | 50.9 GB | ~73.1 GB(est.) |
| llama3.2-vision:90b-instruct-q8_0 | Q8_0 | 88.6 GB | ~127.0 GB(est.) |
| llama3.2-vision:90b-instruct-fp16 | F16 | 165.2 GB | ~236.6 GB(est.) |
Figures marked (est.) approximate the KV cache because this model's architecture details are not published. They are indicative rather than exact.
How to run llama3.2-vision locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run llama3.2-vision:11b - 3.The weights download on first run, then an interactive prompt opens.
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 10.8 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?
- Yes, but slowly. Without a GPU the model runs on the CPU using system RAM, which usually means a few tokens per second rather than dozens. You would need at least 10.8 GB of free RAM for the smallest build.
- 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 run "ollama run llama3.2-vision:11b" in a terminal. The weights download on first use and an interactive session opens.
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.
Model data from the official Ollama registry · verified 13/09/2026