← CanIRunLocal · All hardware · All models
Yes. Bonsai 2 2B (ternary) fits in fast memory on M3 Max (40c GPU) 48GB at Q2_0 (2 GB needed, 36.0 GB usable), about 352 tok/s (estimate).
Hardware: M3 Max (40c GPU) 48GB · Model: Bonsai 2 2B (ternary)
M3 Max (40c GPU) 48GB has 48 GB of unified memory and 400 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 36.0 GB. Bonsai 2 2B (ternary) (2B, Prism ML) at Q2_0 is a 0.91 GB download and needs 2 GB with headroom for about 8k tokens.
| Best quant | Q2_0 |
|---|---|
| Download size | 0.91 GB |
| Memory needed | 2 GB |
| Usable fast memory | 36.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~352 tok/s (estimate) |
| Command | ollama run bonsai-2:2b |
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