Hardware /
Titan Xp
3measured results
160best gen tok/s*
12 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 | 160 | 4,298 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 2 7B | Q4_0 | 76.1 | 1,155 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @c4510dc | Details → |
| Llama 2 7B | Q4_0 | 73.8 | 1,218 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @c4510dc | 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.