gpu4.pics
data via LocalScore
NVIDIA RTX PRO 6000 Blackwell Workstation Edition
95 GB VRAM NVIDIA
running Meta Llama 3.1 8B Instruct· Q4_K_M
103
tokens / sec
1,616 · Excellent #2 of 370
Generation
103tok/s
higher is better
Prompt / prefill
7,237tok/s
higher is better
Time to first token
183 ms
lower is better
Composite score
1,616
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 | 103 | 7,237 | 183 ms | — | — | — | 1,616 |