← CanIRunLocal · All hardware · All models
Yes. Jais 3 MoVA 36B-A4B (MoE) fits in fast memory on M4 Max (40c GPU) 48GB at Q5_K_M (27.9 GB needed, 36.0 GB usable), about 74 tok/s (estimate).
Hardware: M4 Max (40c GPU) 48GB · Model: Jais 3 MoVA 36B-A4B (MoE)
M4 Max (40c GPU) 48GB has 48 GB of unified memory and 546 GB/s of memory bandwidth. Mac Studio M4 Max (40c GPU) 48GB has the same memory and bandwidth, so the fit numbers match; this page is M4 Max (40c GPU) 48GB. The checker leaves macOS a share of unified memory, so Ollama can use 36.0 GB. Jais 3 MoVA 36B-A4B (MoE) (36B, 4B active, IFM) at Q5_K_M is a 26.44 GB download and needs 27.9 GB with headroom for about 8k tokens.
| Best quant | Q5_K_M |
|---|---|
| Download size | 26.44 GB |
| Memory needed | 27.9 GB |
| Usable fast memory | 36.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~74 tok/s (estimate) |
| Command | ollama run hf.co/IFM/Jais-3-MoVA-36B-A4B-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