← CanIRunLocal · All hardware · All models
Yes. Jais 3 32B fits in fast memory on M3 Max (40c GPU) 128GB at BF16 (71.9 GB needed, 96.0 GB usable), about 5 tok/s (estimate).
Hardware: M3 Max (40c GPU) 128GB · Model: Jais 3 32B
M3 Max (40c GPU) 128GB has 128 GB of unified memory and 400 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 96.0 GB. Jais 3 32B (34.78B, IFM) at BF16 is a 69.57 GB download and needs 71.9 GB with headroom for about 8k tokens.
| Best quant | BF16 |
|---|---|
| Download size | 69.57 GB |
| Memory needed | 71.9 GB |
| Usable fast memory | 96.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~5 tok/s (estimate) |
| Command | ollama run hf.co/IFM/Jais-3-32B-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