gpu4.pics
data via LocalScore
AMD Radeon RX 6650 XT
llamafile 0.9.2
8 GB VRAM AMD
running Llama 3.2 1B Instruct· Q4_K_M· 1.5B
82.3
tokens / sec
690 · Strong
Generation
82.3tok/s
higher is better
Prompt / prefill
2,475tok/s
higher is better
Time to first token
620 ms
lower is better
Composite score
690
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 | 82.3 | 2,475 | 620 ms | — | — | — | 690 |