RTX 3060 × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on RTX 3060
214best gen tok/s
6,479best 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 | 214 | 6,358 | LocalScore ↗ | 512+128 | 222 ms | llamafile 0.9.2 |
| Q4_K - Medium | 211 | 6,479 | LocalScore ↗ | 512+128 | 222 ms | llamafile 0.9.2 |
| Q4_K - Medium | 211 | 6,061 | LocalScore ↗ | 512+128 | 229 ms | llamafile 0.9.2 |
| Q4_K - Medium | 206 | 6,119 | LocalScore ↗ | 512+128 | 238 ms | llamafile 0.9.2 |
| Q4_K - Medium | 202 | 5,800 | LocalScore ↗ | 512+128 | 236 ms | llamafile 0.9.2 |
| Q4_K - Medium | 201 | 6,022 | LocalScore ↗ | 512+128 | 236 ms | llamafile 0.9.2 |
| Q4_K - Medium | 197 | 6,058 | LocalScore ↗ | 512+128 | 232 ms | llamafile 0.9.2 |
| Q4_K - Medium | 169 | 6,019 | LocalScore ↗ | 512+128 | 227 ms | llamafile 0.9.2 |
| Q4_K - Medium | 157 | 6,254 | LocalScore ↗ | 512+128 | 222 ms | llamafile 0.9.3 |
| Q4_K - Medium | 70.8 | 5,472 | LocalScore ↗ | 4,352 | 256 ms | llamafile 0.9.3 |
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.
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.