← CanIRunLocal · All hardware · All models
Yes. Ornith-1.5 397B (MoE) fits in fast memory on Mac Studio M3 Ultra (80c GPU) 512GB at Default (246.4 GB needed, 384.0 GB usable), about 3 tok/s (estimate).
Hardware: Mac Studio M3 Ultra (80c GPU) 512GB · Model: Ornith-1.5 397B (MoE)
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. Ornith-1.5 397B (MoE) (397B, Ornith) at Default is a 242 GB download and needs 246.4 GB with headroom for about 8k tokens.
| Best quant | Default |
|---|---|
| Download size | 242 GB |
| Memory needed | 246.4 GB |
| Usable fast memory | 384.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~3 tok/s (estimate) |
| Command | ollama run ornith-1.5:397b |
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