gpu4.pics
data via LocalScore
Quadro RTX 6000
23 GB VRAM NVIDIA
running Llama 3.2 1B Instruct· Q4_K_M· 1.5B
253
tokens / sec
2,526 · Excellent #41 of 768
Generation
253tok/s
higher is better
Prompt / prefill
9,138tok/s
higher is better
Time to first token
143 ms
lower is better
Composite score
2,526
Model size
1.5B
Runtime
—
All benchmarks on this rig
| Model | Quant | Gen | Prompt | TTFT | Power | Perf/W | $/Mtok | Score |
|---|---|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct1.5B | Q4_K_M | 253 | 9,138 | 143 ms | — | — | — | 2,526 |