Hardware /
Tesla K80
4measured results
14.3best gen tok/s*
*Headline excludes tiny/test models (under 0.6B params or TinyStories-style). Open in rig checker →
llama.cpp
| Model | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| Llama 2 7B | Q4_0 | 14.3 | 133 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @32732f2 | Details → |
| Llama 2 7B | Q4_0 | 13.8 | 133 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @32732f2 | Details → |
| Llama 2 7B | Q4_0 | 9.5 | 88.3 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @5d46bab — Running on single GPU | Details → |
| Llama 2 7B | Q4_0 | 9.4 | 89.5 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @5d46bab — Running on single GPU | Details → |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →