gpu4.pics
data via LocalScore
AMD Radeon RX 6650 XT
llamafile 0.9.1
8 GB VRAM AMD
running Llama 3.2 1B Instruct· Q4_K_M· 1.5B
109
tokens / sec
907 · Strong
Generation
109tok/s
higher is better
Prompt / prefill
3,031tok/s
higher is better
Time to first token
443 ms
lower is better
Composite score
907
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 | 109 | 3,031 | 443 ms | — | — | — | 907 |