Llama 2 7B on GTX 1060
28.2best gen tok/s
446best prompt tok/s
640max context tested
2results
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 | 28.2 | 446 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @5fd160b |
| Q4_0 | 27.8 | 417 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @5fd160b |
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.