RTX 4070 Ti SUPER × Llama 2 7B
Llama 2 7B on RTX 4070 Ti SUPER
136best gen tok/s
7,612best 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 | 136 | 6,801 | llama.cpp (Vulkan) ↗ | 512+128 | — | llama.cpp Vulkan @4ae88d0 — coopmat2 |
| Q4_0 | 133 | 7,612 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @9c35706 |
| Q4_0 | 132 | 6,925 | llama.cpp (CUDA) ↗ | 512+128 | — | llama.cpp CUDA @9c35706 |
| Q4_0 | 129 | 6,099 | llama.cpp (Vulkan) ↗ | 512+128 | — | llama.cpp Vulkan @4ae88d0 — 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.