Hardware /
Radeon RX 7900 XT
5measured results
132best gen tok/s*
20 GBreported memory
*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 3.2 1B Instruct | Q4_K - Medium | 132 | 4,185 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 131 | 4,184 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 2 7B | Q4_0 | 123 | 2,942 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @71e74a3 | Details → |
| Llama 2 7B | Q4_0 | 121 | 2,701 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @71e74a3 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 34.6 | 6,502 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →
Includes results from LocalScore, a Mozilla Builders project by cjpais, mirrored in the cn0303/local-llm-speed-benchmarks dataset. LocalScore runs use llamafile, which is built on llama.cpp.