Llama 2 7B on Tesla P4
33.3best gen tok/s
530best 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 | 33.3 | 515 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @c76b420 |
| Q4_0 | 33.1 | 530 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @c76b420 |
| Q4_0 | 28.4 | 287 | llama.cpp (Vulkan) ↗ | 512+128 | — | llama.cpp Vulkan @24d2ee0 |
| Q4_0 | 28.0 | 266 | llama.cpp (Vulkan) ↗ | 512+128 | — | llama.cpp Vulkan @24d2ee0 |
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.