Hardware /
AMD Radeon RX 6800 XT
12measured results
118best gen tok/s*
16 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 | 118 | 4,655 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 110 | 4,585 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 2 7B | Q4_0 | 101 | 1,705 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @N/A | Details → |
| Llama 2 7B | Q4_0 | 100 | 1,753 | llama.cpp (Vulkan) ↗ | 512+128 | llama.cpp Vulkan @N/A | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 96.1 | 4,565 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 39.2 | 975 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 38.2 | 951 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 35.5 | 926 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 22.3 | 517 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 20.5 | 505 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 20.0 | 492 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 12.1 | 3,324 | 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.