← CanIRunLocal · All hardware · All models
Yes. tev1 4B (Together AI, decision) fits in fast memory on RTX 3090 24GB at Q8_0 (5.4 GB needed, 23.5 GB usable), about 122 tok/s (estimate).
Hardware: RTX 3090 24GB · Model: tev1 4B (Together AI, decision)
RTX 3090 24GB has 24 GB of VRAM and 936 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 23.5 GB. Partial offload may also use 60% of that system RAM. tev1 4B (Together AI, decision) (4B, Together AI) at Q8_0 is a 4.6 GB download and needs 5.4 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 4.6 GB |
| Memory needed | 5.4 GB |
| Usable fast memory | 23.5 GB |
| Fit | fits in fast memory |
| Estimated speed | ~122 tok/s (estimate) |
| Command | ollama run tev1:4b-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