GTX 1080 Ti × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on GTX 1080 Ti
153best gen tok/s
4,259best prompt tok/s
640max context tested
5results
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 | 153 | 4,259 | LocalScore ↗ | 512+128 | 298 ms | llamafile 0.9.3 |
| Q4_K - Medium | 146 | 4,068 | LocalScore ↗ | 512+128 | 318 ms | llamafile 0.9.2 |
| Q4_K - Medium | 146 | 4,075 | LocalScore ↗ | 512+128 | 317 ms | llamafile 0.9.2 |
| Q4_K - Medium | 145 | 4,042 | LocalScore ↗ | 512+128 | 306 ms | llamafile 0.9.3 |
| Q4_K - Medium | 144 | 4,047 | LocalScore ↗ | 512+128 | 320 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 GTX 1080 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.