Gemma 4 E2B
28tokens per second
Much faster than reading
First word in 3.4 s · a 300-word answer in about 18 s
Qwen3.5 2B writes 19 tokens per second on the iPhone 14, with the first word in 3.2 s. The fastest model here is Gemma 4 E2B, at 28.
Gemma 4 E2B
28tokens per second
Much faster than reading
First word in 3.4 s · a 300-word answer in about 18 s
Qwen3.5 2B
19tokens per second
Much faster than reading
First word in 3.2 s · a 300-word answer in about 25 s
Loci is free, needs no account, and keeps every conversation on your device.
30-day results and labeled 90-day samples, through · updated daily
Methods, fixed editions and citations · Check model requirements for your device