← CanIRunLocal · All hardware · All models
No. Gemma 3 27B does not fit on M3 Pro 18GB: Q4_K_M needs 19.3 GB and 12.1 GB is usable.
Hardware: M3 Pro 18GB · Model: Gemma 3 27B
M3 Pro 18GB has 18 GB of unified memory and 150 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 12.1 GB. Gemma 3 27B (27.4B, Google) at Q4_K_M is a 17 GB download and needs 19.3 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 17 GB |
| Memory needed | 19.3 GB |
| Usable fast memory | 12.1 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run gemma3:27b |
Smallest hardware that runs it: RTX 3060 12GB at Q4_K_M (partial offload (slower), 19.3 GB needed, 11.5 GB usable, about 5 tok/s (estimate)). Can a RTX 3060 12GB run Gemma 3 27B?
A smaller Google model that fits this hardware: Gemma 3 12B at Q4_K_M (fits in fast memory, 9.8 GB). Can a M3 Pro 18GB run Gemma 3 12B?
Open M3 Pro 18GB in the checkerEstimates, 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