Llama 2 7B on Tesla V100
142best gen tok/s
3,043best prompt tok/s
640max context tested
4results
Measured · all numbers below come from the linked sources
llama.cpp
| Quant | Gen tok/s | Prompt tok/s | Source | Context tested | TTFT | Build |
|---|---|---|---|---|---|---|
| Q4_0 | 142 | 1,411 | llama.cpp (Vulkan) ↗ | 512+128 | — | llama.cpp Vulkan @7d77f07 |
| Q4_0 | 135 | 2,974 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @51f5a45 |
| Q4_0 | 130 | 1,391 | llama.cpp (Vulkan) ↗ | 512+128 | — | llama.cpp Vulkan @7d77f07 |
| Q4_0 | 129 | 3,043 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @51f5a45 |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →
"Context tested" is the largest prompt+generation length actually benchmarked (tokens), not a memory-fit estimate.