← CanIRunLocal · All hardware · All models
Yes. Llama 3.3 70B fits in fast memory on Mac Studio M5 Max (40c GPU) 64GB at Q4_K_M (47.1 GB needed, 48.0 GB usable), about 11 tok/s (estimate).
Hardware: Mac Studio M5 Max (40c GPU) 64GB · Model: Llama 3.3 70B
Mac Studio M5 Max (40c GPU) 64GB has 64 GB of unified memory and 614 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 48.0 GB. Llama 3.3 70B (70.6B, Meta) at Q4_K_M is a 43 GB download and needs 47.1 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 43 GB |
| Memory needed | 47.1 GB |
| Usable fast memory | 48.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~11 tok/s (estimate) |
| Command | ollama run llama3.3:70b |
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