gpu4.pics
data via LocalScore
NVIDIA A100 80GB
80 GB VRAM NVIDIA 400 W TDP
running Qwen2.5 14B Instruct· Q4_K_M· 14.8B
66.3
tokens / sec
614 · Strong #13 of 373
Generation
66.3tok/s
higher is better
Prompt / prefill
2,069tok/s
higher is better
Time to first token
592 ms
lower is better
Composite score
614
Model size
14.8B
Runtime
—
All benchmarks on this rig
| Model | Quant | Gen | Prompt | TTFT | Power | Perf/W | $/Mtok | Score |
|---|---|---|---|---|---|---|---|---|
| Qwen2.5 14B Instruct14.8B | Q4_K_M | 66.3 | 2,069 | 592 ms | — | — | — | 614 |