← CanIRunLocal · All hardware · All models
Yes. pplx-decider 27B (Perplexity, decision) fits in fast memory on M2 Ultra 64GB at Q4_K_M (19.3 GB needed, 48.0 GB usable), about 38 tok/s (estimate).
Hardware: M2 Ultra 64GB · Model: pplx-decider 27B (Perplexity, decision)
M2 Ultra 64GB has 64 GB of unified memory and 800 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 48.0 GB. pplx-decider 27B (Perplexity, decision) (27B, Perplexity) at Q4_K_M is a 17 GB download and needs 19.3 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 17 GB |
| Memory needed | 19.3 GB |
| Usable fast memory | 48.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~38 tok/s (estimate) |
| Command | ollama run pplx-decider:27b |
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