← CanIRunLocal · All hardware · All models
Yes, with partial offload (slower). d3 9B (vLLM Semantic Router, decision) on RTX 4060 8GB at Q8_0 uses system RAM (11.4 GB needed, 7.5 GB usable), about 8 tok/s (estimate).
Hardware: RTX 4060 8GB · Model: d3 9B (vLLM Semantic Router, decision)
RTX 4060 8GB has 8 GB of VRAM and 272 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 7.5 GB. Partial offload may also use 60% of that system RAM. d3 9B (vLLM Semantic Router, decision) (9B, vLLM Semantic Router) at Q8_0 is a 10 GB download and needs 11.4 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 10 GB |
| Memory needed | 11.4 GB |
| Usable fast memory | 7.5 GB |
| Fit | partial offload (slower) |
| Estimated speed | ~8 tok/s (estimate) |
| Command | ollama run d3:9b-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