← CanIRunLocal · All hardware · All models
Yes, with partial offload (slower). Mistral Small 24B on RTX 5070 12GB at Q4_K_M uses system RAM (15.8 GB needed, 11.5 GB usable), about 8 tok/s (estimate).
Hardware: RTX 5070 12GB · Model: Mistral Small 24B
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. Mistral Small 24B (23.6B, Mistral) at Q4_K_M is a 14 GB download and needs 15.8 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 14 GB |
| Memory needed | 15.8 GB |
| Usable fast memory | 11.5 GB |
| Fit | partial offload (slower) |
| Estimated speed | ~8 tok/s (estimate) |
| Command | ollama run mistral-small:24b |
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