0xSero
@0xSero
it's all for you
가입 December 2020
1.9K 팔로잉 중 79.4K 팬
I’m running a fully coherent model fully on my IPhone 15 pro max!
LiquidAI LFM-2.6B in Q8
It did a web search and tool call and dropped facts.
22 tok/s prefill
2-3 tok/s decode
But I could have used q4 for more speed
더 보기
