← CanIRunLocal · All hardware · All models
Yes. Jais 3 MoVA 36B-A4B (MoE) fits in fast memory on DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) at BF16 (76.4 GB needed, 108.8 GB usable), about 19 tok/s (estimate).
Hardware: DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) · Model: Jais 3 MoVA 36B-A4B (MoE)
DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) has 128 GB of unified memory and 273 GB/s of memory bandwidth. DGX OS keeps about 15% of unified memory, so Ollama can use 108.8 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 | 108.8 GB |
| Fit | fits in fast memory |
| Estimated speed | ~19 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