Hardware /
Tesla V100
4measured results
142best 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 | 142 | 1,411 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @7d77f07 | Details → |
| Llama 2 7B | Q4_0 | 135 | 2,974 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @51f5a45 | Details → |
| Llama 2 7B | Q4_0 | 130 | 1,391 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @7d77f07 | Details → |
| Llama 2 7B | Q4_0 | 129 | 3,043 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @51f5a45 | Details → |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →