Llama 2 7B on RTX 5070 Ti
182best gen tok/s
8,420best 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 | 182 | 8,420 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @933414c |
| Q4_0 | 177 | 6,952 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @933414c |
| Q4_0 | 176 | 7,568 | llama.cpp (Vulkan) ↗ | 512+128 | — | llama.cpp Vulkan @0d0764d — coopmat2 |
| Q4_0 | 136 | 6,214 | llama.cpp (Vulkan) ↗ | 512+128 | — | llama.cpp Vulkan @d13d0f6 — coopmat2 |
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.