← CanIRunLocal · All hardware · All models
No. Jais 3 MoVA 36B-A4B (MoE) does not fit on RTX 3080 12GB: Q4_K_M needs 23.9 GB and 11.5 GB is usable.
Hardware: RTX 3080 12GB · Model: Jais 3 MoVA 36B-A4B (MoE)
RTX 3080 12GB has 12 GB of VRAM and 912 GB/s of memory bandwidth. The checker holds back 0.5 GB of VRAM for the driver and assumes 16 GB of system RAM, so fast memory usable by Ollama is 11.5 GB. Partial offload may also use 60% of that system RAM. Jais 3 MoVA 36B-A4B (MoE) (36B, 4B active, IFM) at Q4_K_M is a 22.37 GB download and needs 23.9 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 22.37 GB |
| Memory needed | 23.9 GB |
| Usable fast memory | 11.5 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run hf.co/IFM/Jais-3-MoVA-36B-A4B-GGUF:Q4_K_M |
Smallest hardware that runs it: RTX 4060 Ti 16GB at Q4_K_M (partial offload (slower), 23.9 GB needed, 15.5 GB usable, about 16 tok/s (estimate)). Can a RTX 4060 Ti 16GB run Jais 3 MoVA 36B-A4B (MoE)?
A smaller IFM model that fits this hardware: Jais 3 7B at Q8_0 (fits in fast memory, 10.6 GB). Can a RTX 3080 12GB run Jais 3 7B?
Open RTX 3080 12GB in the checkerEstimates, 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