← CanIRunLocal · All hardware · All models
Yes. DeepSeek R1 Distill Llama 70B fits in fast memory on M2 Max (38c GPU) 96GB at Q4_K_M (47.1 GB needed, 72.0 GB usable), about 7 tok/s (estimate).
Hardware: M2 Max (38c GPU) 96GB · Model: DeepSeek R1 Distill Llama 70B
M2 Max (38c GPU) 96GB has 96 GB of unified memory and 400 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 72.0 GB. DeepSeek R1 Distill Llama 70B (70.6B, DeepSeek) 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 | 72.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~7 tok/s (estimate) |
| Command | ollama run deepseek-r1:70b |
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