Hardware /
GTX 1660 Ti
2measured results
20.1best gen tok/s*
6 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 | |
|---|---|---|---|---|---|---|---|
| qwen2.5-3b-instruct | Q4_0 | 20.1 | 306 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
1 tiny/test model result(s) (excluded from headlines)
| Model | Quant | Gen tok/s | Prompt tok/s | Source | Context tested | Build | |
|---|---|---|---|---|---|---|---|
| Raincandy U TinyStories 656K | Q2_K - Medium | 563 | 40,879 | 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.