← CanIRunLocal · All hardware · All models
Yes. MiniCPM5 2B fits in fast memory on M3 Max (30c GPU) 96GB at F16 (5.8 GB needed, 72.0 GB usable), about 48 tok/s (estimate).
Hardware: M3 Max (30c GPU) 96GB · Model: MiniCPM5 2B
M3 Max (30c GPU) 96GB has 96 GB of unified memory and 300 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 72.0 GB. MiniCPM5 2B (2.52B, OpenBMB) at F16 is a 5.04 GB download and needs 5.8 GB with headroom for about 8k tokens.
| Best quant | F16 |
|---|---|
| Download size | 5.04 GB |
| Memory needed | 5.8 GB |
| Usable fast memory | 72.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~48 tok/s (estimate) |
| Command | ollama run hf.co/openbmb/MiniCPM5-2B-GGUF:F16 |
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