Llama 3.2 Family — local AI model by Meta
Written by Jakub Rusinowski · Last updated
Meta's multimodal and edge-optimized series. Llama 3.2 introduces vision capabilities (11B and 90B variants) and ultra-compact 1B/3B versions designed to run on smartphones and edge devices. All variants feature a 128k context window.
Variants
The smallest Llama 3.2 Family variant needs about 2 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| Llama 3.2 1B Instruct → 1B | ~1.5 GB | 128,000 | ollama run llama3.2:1b | |
| Llama 3.2 3B Instruct → 3B | ~2.7 GB | 128,000 | ollama run llama3.2:3b | |
| Llama 3.2 11B Vision Instruct → 11B | ~7.2 GB | 128,000 | ollama run llama-3-2 | |
| Llama 3.2 90B Vision Instruct → 90B | ~54.4 GB | 128,000 | ollama run llama-3-2 |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Llama 3.2 Family locally
Install Ollama, then pull the tag.
ollama run llama3.2:1bPick a size above for its own VRAM figure, speed estimate and install command.
Licence
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Applies to: Llama 3.2 1B Instruct, Llama 3.2 3B Instruct, Llama 3.2 11B Vision Instruct, Llama 3.2 90B Vision InstructRecommended GPU
The cheapest catalogued GPU that runs Llama 3.2 Family locally (min 2 GB VRAM) is the Intel Arc B570 (10 GB).
Can I run Llama 3.2 Family on my GPU?
- Llama 3.2 Family on AMD Radeon RX 9060 XT 8GB
- Llama 3.2 Family on AMD Ryzen AI Max+ 395
- Llama 3.2 Family on Apple M1 Ultra
- Llama 3.2 Family on Apple M2 Max
- Llama 3.2 Family on Apple M4 Max
- Llama 3.2 Family on Apple M5 Max
- Llama 3.2 Family on Intel Arc B570
- Llama 3.2 Family on Intel Arc B580
- Llama 3.2 Family on NVIDIA A100 80GB (PCIe)
- Llama 3.2 Family on NVIDIA DGX Spark
- Llama 3.2 Family on NVIDIA GeForce RTX 3060 (12GB)
- Llama 3.2 Family on NVIDIA GeForce RTX 3070
- Llama 3.2 Family on NVIDIA GeForce RTX 3070 Ti
- Llama 3.2 Family on NVIDIA GeForce RTX 3080 (10GB)
- Llama 3.2 Family on NVIDIA GeForce RTX 4060
- Llama 3.2 Family on NVIDIA GeForce RTX 4070
- Llama 3.2 Family on NVIDIA GeForce RTX 4070 Super
- Llama 3.2 Family on NVIDIA GeForce RTX 4070 Ti
- Llama 3.2 Family on NVIDIA GeForce RTX 5060
- Llama 3.2 Family on NVIDIA GeForce RTX 5060 Ti 8GB
- Llama 3.2 Family on NVIDIA GeForce RTX 5070
- Llama 3.2 Family on NVIDIA H100 80GB (PCIe)
- Llama 3.2 Family on NVIDIA RTX PRO 6000 Blackwell
Llama 3.2 Family — frequently asked questions
How much VRAM does Llama 3.2 Family need?
Llama 3.2 Family needs about 2 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Llama 3.2 1B Instruct (2 GB, Q4_K_M); Llama 3.2 3B Instruct (3 GB, Q4_K_M); Llama 3.2 11B Vision Instruct (7 GB, Q4_K_M); Llama 3.2 90B Vision Instruct (54 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Llama 3.2 Family on an RTX 4090 (24 GB)?
Yes — Llama 3.2 Family runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for Llama 3.2 Family?
Q4_K_M is the best balance of quality and VRAM for Llama 3.2 Family in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run Llama 3.2 Family with Ollama?
Install Ollama, then run: ollama run llama3.2:1b. This downloads Llama 3.2 Family and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.