← CanIRunLocal · All hardware · All models
Yes. Jais 3 3.7B fits in fast memory on Mac Studio M5 Max (40c GPU) 64GB at BF16 (11 GB needed, 48.0 GB usable), about 48 tok/s (estimate).
Hardware: Mac Studio M5 Max (40c GPU) 64GB · Model: Jais 3 3.7B
Mac Studio M5 Max (40c GPU) 64GB has 64 GB of unified memory and 614 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 48.0 GB. Jais 3 3.7B (5.06B, IFM) at BF16 is a 10.13 GB download and needs 11 GB with headroom for about 8k tokens.
| Best quant | BF16 |
|---|---|
| Download size | 10.13 GB |
| Memory needed | 11 GB |
| Usable fast memory | 48.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~48 tok/s (estimate) |
| Command | ollama run hf.co/IFM/Jais-3-3.7B-GGUF:BF16 |
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