← CanIRunLocal · All hardware · All models
Yes. Jais 3 7B fits in fast memory on RTX 5070 12GB at Q8_0 (10.6 GB needed, 11.5 GB usable), about 42 tok/s (estimate).
Hardware: RTX 5070 12GB · Model: Jais 3 7B
RTX 5070 12GB has 12 GB of VRAM and 672 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 7B (9B, IFM) at Q8_0 is a 9.57 GB download and needs 10.6 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 9.57 GB |
| Memory needed | 10.6 GB |
| Usable fast memory | 11.5 GB |
| Fit | fits in fast memory |
| Estimated speed | ~42 tok/s (estimate) |
| Command | ollama run hf.co/IFM/Jais-3-7B-GGUF:Q8_0 |
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