gpu4.pics
data via LocalScore
NVIDIA H100
80 GB VRAM NVIDIA 700 W TDP
running Meta Llama 3.1 8B Instruct· Q4_K_M
120
tokens / sec
1,382 · Excellent #5 of 370
Generation
120tok/s
higher is better
Prompt / prefill
5,202tok/s
higher is better
Time to first token
236 ms
lower is better
Composite score
1,382
Model size
8B
Runtime
—
All benchmarks on this rig
| Model | Quant | Gen | Prompt | TTFT | Power | Perf/W | $/Mtok | Score |
|---|---|---|---|---|---|---|---|---|
| Meta Llama 3.1 8B Instruct | Q4_K_M | 120 | 5,202 | 236 ms | — | — | — | 1,382 |