Hardware /
Apple M3 Ultra
1measured results
116best gen tok/s*
*Headline excludes tiny/test models (under 0.6B params or TinyStories-style). Open in rig checker →
llama.cpp
| Model | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| Llama 2 7B | Q4_0 | 116 | 1,117 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @2d451c8 — MoltenVK | Details → |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →