Hardware /

AMD Radeon RX 6750 XT

2measured results
82.3best gen tok/s*

*Headline excludes tiny/test models (under 0.6B params or TinyStories-style). Open in rig checker →

llama.cpp

ModelQuantGen tok/sPrompt tok/sSourceContext testedBuild
Llama 2 7BQ4_082.3997llama.cpp (Vulkan) ↗512+128llama.cpp Vulkan @228f34cDetails →
Llama 2 7BQ4_082.01,041llama.cpp (Vulkan) ↗512+128llama.cpp Vulkan @228f34cDetails →

Ollama

No measured Ollama results yet. Submit yours →

MLX

No measured MLX results yet. Submit yours →