Hardware /
Tesla P100
4measured results
66.5best 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 | 66.5 | 686 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @eec1e33 | Details → |
| Llama 2 7B | Q4_0 | 63.2 | 678 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @eec1e33 | Details → |
| Llama 2 7B | Q4_0 | 62.0 | 787 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @b8372ee | Details → |
| Llama 2 7B | Q4_0 | 58.4 | 761 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @b8372ee | Details → |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →