Quadro P620 × Llama 3.2 1B Instruct
Llama 3.2 1B Instruct on Quadro P620
26.6best gen tok/s
613best prompt tok/s
4,352max context tested
3results
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 | 26.6 | 613 | LocalScore ↗ | 4,352 | 2,253 ms | llamafile 0.9.2 |
| Q4_K - Medium | 26.4 | 611 | LocalScore ↗ | 4,352 | 2,250 ms | llamafile 0.9.2 |
| Q4_K - Medium | 18.6 | 330 | LocalScore ↗ | 4,352 | 5,300 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 Quadro P620 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.