Hardware /
RTX 4060 Ti
38measured results
219best gen tok/s*
8 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 | 219 | 9,424 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 218 | 9,337 | LocalScore ↗ | 512+128 | llamafile 0.9.1 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 218 | 9,134 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 216 | 9,463 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 214 | 9,161 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 176 | 8,411 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 176 | 8,835 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 174 | 8,575 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 171 | 8,699 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 106 | 8,549 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Gemma 3 4b It | Q4_K - Medium | 74.4 | 4,885 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 2 7B | Q4_0 | 64.0 | 3,803 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @89d1029 | Details → |
| Llama 2 7B | Q4_0 | 63.9 | 3,395 | llama.cpp (CUDA) ↗ | 512+128 | llama.cpp CUDA @89d1029 | Details → |
| Gemma 3 4b It Qat | Q4_0 | 63.0 | 4,859 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 52.6 | 6,655 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Llama 3.2 1B Instruct | Q4_K - Medium | 52.5 | 6,597 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 49.6 | 2,130 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 49.3 | 2,247 | LocalScore ↗ | 512+128 | llamafile 0.9.1 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 49.1 | 2,267 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 45.4 | 2,231 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 45.4 | 2,224 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 44.9 | 2,182 | LocalScore ↗ | 4,352 | llamafile 0.9.3 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 44.8 | 2,217 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 42.8 | 1,843 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| gemma-2-9b-it | Q4_K - Medium | 32.4 | 1,820 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 30.7 | 2,112 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 27.1 | 1,205 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Amoral Gemma3 12B | Q4_K - Medium | 26.9 | 1,582 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 26.9 | 1,266 | LocalScore ↗ | 512+128 | llamafile 0.9.1 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 26.8 | 1,260 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 26.2 | 1,260 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 24.5 | 1,241 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 24.3 | 1,234 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 23.4 | 1,205 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| gemma2 | Q8_0 | 21.9 | 1,787 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Meta Llama 3.1 8B Instruct | Q4_K - Medium | 20.6 | 1,929 | LocalScore ↗ | 512+128 | llamafile 0.9.2 | Details → |
| Qwen3 14B | Q4_K - Medium | 11.9 | 1,091 | LocalScore ↗ | 512+128 | llamafile 0.9.3 | Details → |
| Qwen2.5 14B Instruct | Q4_K - Medium | 3.5 | 327 | 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.