← CanIRunLocal · All hardware · All models
Yes. Llama 3.2 Vision 11B fits in fast memory on RTX 5070 12GB at Q4_K_M (9.3 GB needed, 11.5 GB usable), about 52 tok/s (estimate).
Hardware: RTX 5070 12GB · Model: Llama 3.2 Vision 11B
RTX 5070 12GB has 12 GB of VRAM and 672 GB/s of memory bandwidth. The checker holds back 0.5 GB of VRAM for the driver and assumes 16 GB of system RAM, so fast memory usable by Ollama is 11.5 GB. Partial offload may also use 60% of that system RAM. Llama 3.2 Vision 11B (10.7B, Meta) at Q4_K_M is a 7.8 GB download and needs 9.3 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 7.8 GB |
| Memory needed | 9.3 GB |
| Usable fast memory | 11.5 GB |
| Fit | fits in fast memory |
| Estimated speed | ~52 tok/s (estimate) |
| Command | ollama run llama3.2-vision:11b |
Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-23.
A project by OnDevice Labs · llms.txt