← CanIRunLocal · All hardware · All models
Yes. Jais 3 32B fits in fast memory on M4 Max (32c GPU) 36GB at Q5_K_M (27 GB needed, 27.0 GB usable), about 13 tok/s (estimate).
Hardware: M4 Max (32c GPU) 36GB · Model: Jais 3 32B
M4 Max (32c GPU) 36GB has 36 GB of unified memory and 410 GB/s of memory bandwidth. Mac Studio M4 Max (32c GPU) 36GB has the same memory and bandwidth, so the fit numbers match; this page is M4 Max (32c GPU) 36GB. The checker leaves macOS a share of unified memory, so Ollama can use 27.0 GB. Jais 3 32B (34.78B, IFM) at Q5_K_M is a 24.7 GB download and needs 27 GB with headroom for about 8k tokens.
| Best quant | Q5_K_M |
|---|---|
| Download size | 24.7 GB |
| Memory needed | 27 GB |
| Usable fast memory | 27.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~13 tok/s (estimate) |
| Command | ollama run hf.co/IFM/Jais-3-32B-GGUF:Q5_K_M |
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