Ollama on the NVIDIA RTX 5070 Ti
llamaperf has 6 Ollama reports on the NVIDIA RTX 5070 Ti, 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.
6 Ollama reports on the NVIDIA RTX 5070 Ti
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.
- Gemma 4 · Q4_K_M9.3 t/s
- Gemma 4 · Q4_K_M102.9 t/s
- Gemma 4 · Q4_K_M78.6 t/s
- Gemma 4 · Q4_K_M148.2 t/s
- Gemma 4 · Q4_K_M226.3 t/s
- Ornith1.5 35B · 3B active · Q4_K_M180.0 t/s(2 cards)
Frequently asked
How fast is Ollama on the NVIDIA RTX 5070 Ti?
llamaperf has 6 Ollama reports on the NVIDIA RTX 5070 Ti, 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.