gpu4.pics
data via LocalScore
NVIDIA RTX 6000 Ada Generation
48 GB VRAM NVIDIA
running Llama 3.2 1B Instruct· Q4_K_M· 1.5B
131
tokens / sec
3,350 · Excellent #13 of 768
Generation
131tok/s
higher is better
Prompt / prefill
19,620tok/s
higher is better
Time to first token
68 ms
lower is better
Composite score
3,350
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 | 131 | 19,620 | 68 ms | — | — | — | 3,350 |