cygnal/Qwen3.8-Flash-Next-Heretic2-IQ4XS-NGQ4-GGUF Image-Text-to-Text โข 177B โข Updated Sep 19 โข 32.4k โข 8
kingjones777/DeepSeek-V4-Flash-180B-ROCmFP4-STRIX_LEAN-GGUF Text Generation โข 180B โข Updated Sep 1 โข 111 โข 6
orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF Image-Text-to-Text โข 177B โข Updated 25 days ago โข 673k โข 1.55k
view post Post 8,600 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 10 10 ๐ 3 3 + Reply