Can I run Llama 3.2 Vision?

Multimodal Llama — image understanding plus chat. 11B fits a 16GB+ Mac.

visionchat · sizes: 11B · Llama 3.2 Community

What runs it

machine	best fit	verdict	speed
Apple M1 · 8GB	11B Q4_K_M	❌ Won't fit	—
Apple M1 Pro · 16GB	11B Q4_K_M	✅ Runs (tight)	14–25 tok/s
Apple M2 · 16GB	11B Q4_K_M	✅ Runs (tight)	8–13 tok/s
Apple M3 Pro · 18GB	11B Q4_K_M	✅ Runs (tight)	11–18 tok/s
Apple M2 Pro · 32GB	11B Q8_0	✅ Runs comfortably	9–15 tok/s
Apple M4 Pro · 48GB	11B Q8_0	✅ Runs comfortably	11–19 tok/s
Apple M3 Max · 36GB	11B Q8_0	✅ Runs comfortably	15–25 tok/s
Apple M2 Max · 64GB	11B Q8_0	✅ Runs comfortably	15–25 tok/s
Apple M4 Max · 128GB	11B Q8_0	✅ Runs comfortably	19–30 tok/s
Apple M2 Ultra · 192GB	11B Q8_0	✅ Runs comfortably	20–35 tok/s
NVIDIA GeForce RTX 3060 · 12GB VRAM	11B Q4_K_M	✅ Runs comfortably	20–35 tok/s
NVIDIA GeForce RTX 4070 · 12GB VRAM	11B Q4_K_M	✅ Runs comfortably	30–45 tok/s
NVIDIA GeForce RTX 4090 · 24GB VRAM	11B Q8_0	✅ Runs comfortably	35–60 tok/s
NVIDIA GeForce RTX 5080 · 16GB VRAM	11B Q8_0	✅ Runs (tight)	30–50 tok/s
NVIDIA GeForce RTX 5090 · 32GB VRAM	11B Q8_0	✅ Runs comfortably	60–100 tok/s
AMD Radeon RX 7900 XTX · 24GB VRAM	11B Q8_0	✅ Runs comfortably	30–50 tok/s