gpu4.pics
data via LocalScore
Apple M1
llamafile 0.9.2
8 GB unified Apple
running Llama 3.2 1B Instruct· Q4_K_M· 1.5B
40.7
tokens / sec
228 · Modest
Generation
40.7tok/s
higher is better
Prompt / prefill
615tok/s
higher is better
Time to first token
2.11 s
lower is better
Efficiency
5.09 tok/s/W
Electricity cost
$0.009/Mtok
Power draw
8 W
All benchmarks on this rig
| Model | Quant | Gen | Prompt | TTFT | Power | Perf/W | $/Mtok | Score |
|---|---|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct1.5B | Q4_K_M | 40.7 | 615 | 2.11 s | 8 W | 5.09 tok/s/W | $0.009/Mtok | 228 |