llama.cpp on the NVIDIA RTX 5070
llamaperf has 4 llama.cpp reports on the NVIDIA RTX 5070, 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.
4 llama.cpp reports on the NVIDIA RTX 5070
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 125B · 6B active · UD-IQ3_XXS11.5 t/s(part in system RAM)
- Model not identifiedPP 1800.0 t/s
- Qwen3.8 125B · 6B active · IQ3_XXS15.0 t/s(part in system RAM)
- Qwen3.8 125B · 6B active · IQ1_S22.0 t/s(part in system RAM)
Frequently asked
How fast is llama.cpp on the NVIDIA RTX 5070?
llamaperf has 4 llama.cpp reports on the NVIDIA RTX 5070, 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.