← CanIRunLocal · All hardware · All models
Yes, with partial offload (slower). Ministral 3 14B on RTX 3060 8GB at Q4_K_M uses system RAM (10.7 GB needed, 7.5 GB usable), about 9 tok/s (estimate).
Hardware: RTX 3060 8GB · Model: Ministral 3 14B
RTX 3060 8GB has 8 GB of VRAM and 240 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 7.5 GB. Partial offload may also use 60% of that system RAM. Ministral 3 14B (13.9B, Mistral) at Q4_K_M is a 9.1 GB download and needs 10.7 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 9.1 GB |
| Memory needed | 10.7 GB |
| Usable fast memory | 7.5 GB |
| Fit | partial offload (slower) |
| Estimated speed | ~9 tok/s (estimate) |
| Command | ollama run ministral-3:14b |
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