nvidia/NVIDIA-Nemotron-Nano-12B-v2 Text Generation β’ 12B β’ Updated 3 days ago β’ 20.1k β’ β’ 135
view post Post 6105 LiquidAI/LFM2-8B-A1B just dropped!8.3B params with only 1.5B active/token π> Quality β 3β4B dense, yet faster than Qwen3-1.7B> MoE designed to run on phones/laptops (llama.cpp / vLLM)> Pre-trained on 12T tokens β strong math/code/IF See translation 1 reply Β· π₯ 7 7 π 3 3 + Reply