Hardware /
GTX 1060 3GB
3measured results
98.7best gen tok/s*
3 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 0.5B Instruct | Q4_K - Medium | 98.7 | 3,114 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| tinyllama_tinyllama-1.1b-chat-v1.0 | Q4_K - Medium | 71.4 | 1,509 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| DeepSeek R1 Distill Qwen 1.5B | IQ4_XS - 4.25 bpw | 8.4 | 107 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | 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.