Llama 2 7B on GTX 1660
41.4best gen tok/s
154best 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 | 41.4 | 154 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @9515c61 |
| Q4_0 | 41.4 | 149 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @9515c61 |
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.