RTX 3080 Ti × Meta Llama 3.1 8B Instruct
Meta Llama 3.1 8B Instruct on RTX 3080 Ti
104best gen tok/s
3,739best prompt tok/s
4,352max context tested
4results
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 | 104 | 3,739 | LocalScore ↗ | 512+128 | 343 ms | llamafile 0.9.2 |
| Q4_K - Medium | 84.0 | 3,407 | LocalScore ↗ | 4,352 | 378 ms | llamafile 0.9.3 |
| Q4_K - Medium | 81.3 | 3,482 | LocalScore ↗ | 512+128 | 367 ms | llamafile 0.9.3 |
| Q4_K - Medium | 79.2 | 3,204 | LocalScore ↗ | 4,352 | 395 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.
What else can RTX 3080 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.