Maxime Labonne
@maximelabonne
Head of Post-Training @liquidai
🤗 HF:
📝 Blog:
加入 October 2017
574 正在關注 39.6K 粉絲
You can't stop us from going smaller.
So you’re telling me I can swap my local LFM2.5-2.6B from F16 to QAD Q4_0 and go from:
5.4 GB → 1.6 GB
21 → 64 tok/s
3.0s → 1.2s tool-call latency
while keeping ~97% of BF16 performance?
@LiquidAI what did you just do 😭
顯示更多
