Llama 2 7B on Tesla M40
41.7best gen tok/s
290best 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 | 41.7 | 93.3 | llama.cpp (Vulkan) ↗ | 512+128 | — | llama.cpp Vulkan @b8372ee |
| Q4_0 | 40.0 | 290 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @97d5117 |
| Q4_0 | 39.4 | 92.5 | llama.cpp (Vulkan) ↗ | 512+128 | — | llama.cpp Vulkan @b8372ee |
| Q4_0 | 38.0 | 283 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @97d5117 |
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.