view post Post 8368 LiquidAI/LFM2-8B-A1B just dropped!8.3B params with only 1.5B active/token ๐> Quality โ 3โ4B dense, yet faster than Qwen3-1.7B> MoE designed to run on phones/laptops (llama.cpp / vLLM)> Pre-trained on 12T tokens โ strong math/code/IF See translation 1 reply ยท ๐ฅ 9 9 ๐ 3 3 + Reply
Running Featured 134 Qwen3 Livetranslate Demo ๐ 134 Translate speech live with text and audio output