ML-Intern-lab/Qwen3.5-0.8B-weight-space-programming Image-Text-to-Text • 0.9B • Updated about 15 hours ago • 35 • 47
view article Article TFLOPS Gap: Why FP4 MoE Kernel Engineering Matters on Blackwell apsys • Jan 5 • 15
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases Paper • 2402.14905 • Published Feb 22, 2024 • 135