gpu4.pics
data via LocalScore
NVIDIA RTX 4080
16 GB VRAM NVIDIA 320 W TDP
running Qwen2.5 14B Instruct· Q4_K_M· 14.8B
46.2
tokens / sec
651 · Strong #11 of 373
Generation
46.2tok/s
higher is better
Prompt / prefill
2,803tok/s
higher is better
Time to first token
468 ms
lower is better
Composite score
651
Model size
14.8B
Runtime
—
All benchmarks on this rig
| Model | Quant | Gen | Prompt | TTFT | Power | Perf/W | $/Mtok | Score |
|---|---|---|---|---|---|---|---|---|
| Qwen2.5 14B Instruct14.8B | Q4_K_M | 46.2 | 2,803 | 468 ms | — | — | — | 651 |