← CanIRunLocal · All hardware · All models
No. Bonsai 2 27B (ternary) does not fit on M3 8GB: Q2_0 needs 10.6 GB and 5.4 GB is usable.
Hardware: M3 8GB · Model: Bonsai 2 27B (ternary)
M3 8GB has 8 GB of unified memory and 100 GB/s of memory bandwidth. M2 8GB has the same memory and bandwidth, so the fit numbers match; this page is M3 8GB. The checker leaves macOS a share of unified memory, so Ollama can use 5.4 GB. Bonsai 2 27B (ternary) (27B, Prism ML) at Q2_0 is a 8.3 GB download and needs 10.6 GB with headroom for about 8k tokens.
| Best quant | Q2_0 |
|---|---|
| Download size | 8.3 GB |
| Memory needed | 10.6 GB |
| Usable fast memory | 5.4 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run bonsai-2:27b |
Smallest hardware that runs it: RTX 3060 8GB at Q2_0 (partial offload (slower), 10.6 GB needed, 7.5 GB usable, about 10 tok/s (estimate)). Can a RTX 3060 8GB run Bonsai 2 27B (ternary)?
A smaller Prism ML model that fits this hardware: Bonsai 2 9B (ternary) at Q2_0 (fits in fast memory, 4.6 GB). Can a M3 8GB run Bonsai 2 9B (ternary)?
Open M3 8GB in the checkerEstimates, 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