← CanIRunLocal · All hardware · All models
Yes. Jais 3 MoVA 36B-A4B (MoE) fits in fast memory on M4 Max (40c GPU) 128GB at BF16 (76.4 GB needed, 96.0 GB usable), about 26 tok/s (estimate).
Hardware: M4 Max (40c GPU) 128GB · Model: Jais 3 MoVA 36B-A4B (MoE)
M4 Max (40c GPU) 128GB has 128 GB of unified memory and 546 GB/s of memory bandwidth. Mac Studio M4 Max (40c GPU) 128GB has the same memory and bandwidth, so the fit numbers match; this page is M4 Max (40c GPU) 128GB. The checker leaves macOS a share of unified memory, so Ollama can use 96.0 GB. Jais 3 MoVA 36B-A4B (MoE) (36B, 4B active, IFM) at BF16 is a 74.92 GB download and needs 76.4 GB with headroom for about 8k tokens.
| Best quant | BF16 |
|---|---|
| Download size | 74.92 GB |
| Memory needed | 76.4 GB |
| Usable fast memory | 96.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~26 tok/s (estimate) |
| Command | ollama run hf.co/IFM/Jais-3-MoVA-36B-A4B-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