RTX 5060 Ti × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on RTX 5060 Ti
309best gen tok/s
11,156best prompt tok/s
4,352max context tested
10results
Measured · all numbers below come from the linked sources
llama.cpp
| Quant | Gen tok/s | Prompt tok/s | Source | Context tested | TTFT | Build |
|---|---|---|---|---|---|---|
| Q4_K - Medium | 309 | 11,156 | LocalScore ↗ | 4,352 | 133 ms | llamafile 0.9.2 |
| Q4_K - Medium | 236 | 9,991 | LocalScore ↗ | 512+128 | 148 ms | llamafile 0.9.2 |
| Q4_K - Medium | 226 | 9,965 | LocalScore ↗ | 512+128 | 145 ms | llamafile 0.9.2 |
| Q4_K - Medium | 220 | 9,950 | LocalScore ↗ | 512+128 | 144 ms | llamafile 0.9.2 |
| Q4_K - Medium | 216 | 10,380 | LocalScore ↗ | 4,352 | 1,202 ms | llamafile 0.9.2 |
| Q4_K - Medium | 191 | 9,159 | LocalScore ↗ | 512+128 | 168 ms | llamafile 0.9.2 |
| Q4_K - Medium | 190 | 8,921 | LocalScore ↗ | 512+128 | 2,820 ms | llamafile 0.9.2 |
| Q4_K - Medium | 103 | 8,234 | LocalScore ↗ | 512+128 | 177 ms | llamafile 0.9.2 |
| Q4_K - Medium | 97.9 | 8,630 | LocalScore ↗ | 512+128 | 165 ms | llamafile 0.9.2 |
| Q4_K - Medium | 91.9 | 6,509 | LocalScore ↗ | 512+128 | 423 ms | llamafile 0.9.2 |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →
"Context tested" is the largest prompt+generation length actually benchmarked (tokens), not a memory-fit estimate.
What else can RTX 5060 Ti run? →
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.