Llama 2 7B on AMD FirePro D700
16.6best gen tok/s
70.0best prompt tok/s
640max context tested
1results
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 | 16.6 | 70.0 | llama.cpp (Vulkan) ↗ | 512+128 | — | llama.cpp Vulkan @d3bd719 — MoltenVK, running in FP16 mode on FP32 only chip |
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.