llama.cpp on the NVIDIA RTX 5080
llamaperf has 7 llama.cpp reports on the NVIDIA RTX 5080, 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.
7 llama.cpp reports on the NVIDIA RTX 5080
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 · Q3_K_XL80.0 t/s(speculative decoding)
- Qwen3.8 125B · 6B active · Q5_K_XLPP 100.0 t/s(2 cards, speculative decoding, part in system RAM)
- Qwen3.8 27B · NVFP412.0 t/s
- Qwen3.8 125B · 6B active · IQ3_XXS6.0 t/s(part in system RAM)
- Qwen3.8 27B · IQ4_XS75.0 t/s(speculative decoding)
- Qwen3.8 27B · Q4_K_M13.2 t/s(part in system RAM)
- Qwen3.6 35B · 3B active · Q4_K_XL56.0 t/s(part in system RAM)
Frequently asked
How fast is llama.cpp on the NVIDIA RTX 5080?
llamaperf has 7 llama.cpp reports on the NVIDIA RTX 5080, 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.