AMD Radeon Instinct MI50 × Llama 2 7B
Llama 2 7B on AMD Radeon Instinct MI50
118best gen tok/s
1,127best 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 | 118 | 1,127 | llama.cpp (Vulkan) ↗ | 512+128 | — | llama.cpp Vulkan @3af34b9 |
| Q4_0 | 109 | 1,120 | llama.cpp (Vulkan) ↗ | 512+128 | — | llama.cpp Vulkan @3af34b9 |
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.