← CanIRunLocal · All hardware · All models
Yes. Bonsai 2 9B (ternary) fits in fast memory on Mac Studio M3 Ultra (80c GPU) 512GB at Q2_0 (4.6 GB needed, 384.0 GB usable), about 205 tok/s (estimate).
Hardware: Mac Studio M3 Ultra (80c GPU) 512GB · Model: Bonsai 2 9B (ternary)
Mac Studio M3 Ultra (80c GPU) 512GB has 512 GB of unified memory and 819 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 384.0 GB. Bonsai 2 9B (ternary) (9B, Prism ML) at Q2_0 is a 3.2 GB download and needs 4.6 GB with headroom for about 8k tokens.
| Best quant | Q2_0 |
|---|---|
| Download size | 3.2 GB |
| Memory needed | 4.6 GB |
| Usable fast memory | 384.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~205 tok/s (estimate) |
| Command | ollama run bonsai-2:9b |
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