gpu4.pics
data via LocalScore
NVIDIA GeForce RTX 4060 Ti
llamafile 0.9.2
16 GB VRAM NVIDIA
running Llama 3.2 1B Instruct· Q4_K_M· 1.5B
216
tokens / sec
2,318 · Excellent
Generation
216tok/s
higher is better
Prompt / prefill
9,463tok/s
higher is better
Time to first token
164 ms
lower is better
Composite score
2,318
Model size
1.5B
Runtime
llamafile
All benchmarks on this rig
| Model | Quant | Gen | Prompt | TTFT | Power | Perf/W | $/Mtok | Score |
|---|---|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct1.5B | Q4_K_M | 216 | 9,463 | 164 ms | — | — | — | 2,318 |