Tight fit
Running Llama 3.2 11B Vision Instruct on NVIDIA GeForce RTX 3080 16GB (Mobile)
Llama 3.2 11B Vision Instruct fits at Q8_0, but headroom is tight (0 GB). Reduce context or use a smaller quant for safety.
Model size
11B params
Llama 3.2 11B Vision Instruct →Memory available
Recommended quant
Q8_0
Highest quality that fits
Quick start with Ollama
1. Install
ollama pull llama3.2-vision:11b2. Run
ollama run llama3.2-vision:11bDefault quant in Ollama is Q4_K_M. To use a different quant, append it: llama3.2-vision:11b-q5_K_M.
Variants and what fits
| Quantization | File size | VRAM required | Fits on NVIDIA GeForce RTX 3080 16GB (Mobile)? |
|---|---|---|---|
| Q4_K_M | 7.9 GB | 11 GB | Yes |
| Q8_0 | 12.5 GB | 16 GB | Yes |
Real benchmarks
Frequently asked
Can NVIDIA GeForce RTX 3080 16GB (Mobile) run Llama 3.2 11B Vision Instruct?
Llama 3.2 11B Vision Instruct fits at Q8_0, but headroom is tight (0 GB). Reduce context or use a smaller quant for safety.
What quantization should I use?
Q8_0 is the highest-quality variant of Llama 3.2 11B Vision Instruct that fits in 16 GB VRAM. Lower-bit quants will be smaller but lose some quality.
How fast will it be?
Measured at 67.0 tok/s on this combination in our testing.
See also: Llama 3.2 11B Vision Instruct, NVIDIA GeForce RTX 3080 16GB (Mobile), all benchmarks.
Reviewed by RunLocalAI Editorial. See our editorial policy.