Running 1 One training step of a 1,024-GPU MoE 🏙 1 Explore a live 1,024‑GPU MoE training step in your browser
Running on CPU Upgrade 379 The Ultimate MoE Training Handbook 🧩 379 A hands-on guide to training Mixture-of-Experts models
deepseek-ai/DeepSeek-V4.1-Flash-1017 Image-Text-to-Text • 763B • Updated 22 days ago • 296k • • 5.41k
Running 181 HF Viewer · Model Architecture Explorer 🟩 181 Interactive architecture graph for any HF model
Running Featured 86 QED-Nano: Teaching a Tiny Model to Prove Hard Theorems 📝 86 Who needs 1T parameters? Olympiad proofs with a 4B model