← CanIRunLocal · All hardware · All models
Yes. strands-decider 2B (Strands Agents, decision) fits in fast memory on Mac Studio M4 Max (40c GPU) 128GB at Default (2.7 GB needed, 96.0 GB usable), about 218 tok/s (estimate).
Hardware: Mac Studio M4 Max (40c GPU) 128GB · Model: strands-decider 2B (Strands Agents, decision)
Mac Studio M4 Max (40c GPU) 128GB has 128 GB of unified memory and 546 GB/s of memory bandwidth. M4 Max (40c GPU) 128GB has the same memory and bandwidth, so the fit numbers match; this page is Mac Studio M4 Max (40c GPU) 128GB. The checker leaves macOS a share of unified memory, so Ollama can use 96.0 GB. strands-decider 2B (Strands Agents, decision) (2B, Strands Agents) at Default is a 2 GB download and needs 2.7 GB with headroom for about 8k tokens.
| Best quant | Default |
|---|---|
| Download size | 2 GB |
| Memory needed | 2.7 GB |
| Usable fast memory | 96.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~218 tok/s (estimate) |
| Command | ollama run strands-decider: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