Ollama on the NVIDIA RTX 3090
llamaperf has 3 Ollama reports on the NVIDIA RTX 3090, none of them a plain single-card run with a model size and quant, so there is no median to quote. The reports are listed below with how each one ran.
3 Ollama reports on the NVIDIA RTX 3090
Newest first. A run on several cards, with speculative decoding, with part of the model in system RAM or with batched requests says so, since each describes a different setup.
- Qwen3.8 27B · IQ3_S83.0 t/s(speculative decoding)
- Qwen3.8 27B · Q460.0 t/s(2 cards, speculative decoding)
- Qwen3.6 35B · 3B active112.4 t/s(part in system RAM)
Frequently asked
How fast is Ollama on the NVIDIA RTX 3090?
llamaperf has 3 Ollama reports on the NVIDIA RTX 3090, none of them a plain single-card run with a model size and quant, so there is no median to quote. The reports are listed below with how each one ran.