gpu4.pics
data via LocalScore
NVIDIA RTX A6000
48 GB VRAM NVIDIA 300 W TDP
running Llama 3.2 1B Instruct· Q4_K_M· 1.5B
315
tokens / sec
3,438 · Excellent #12 of 768
Generation
315tok/s
higher is better
Prompt / prefill
13,191tok/s
higher is better
Time to first token
102 ms
lower is better
Composite score
3,438
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 | 315 | 13,191 | 102 ms | — | — | — | 3,438 |