view article Article Fine-Tuning Coding Agents on a 16GB Mac: PyTorch MPS vs. Apple MLX harshitkgupta • 14 days ago • 3
Tiny non-Transformers Collection Any model that is not pure transformers, so both RWKV, Mamba like models and hybrid like Jamba will be showed. MODELS OF THE SAME FAMILY DONT GET NOTE • 17 items • Updated 16 days ago • 2
view article Article Trained 210M text-to-image model from scratch on one GPU: what actually mattered ivanmikhnenkov • Sep 9 • 10
view article Article BananaMind 2 Pro: We've (almost) matched SmolLM2 at 20x fewer tokens... Trained On a 5070 Ti Banaxi-Tech • 23 days ago • 7
Siel5732’s Booth Collection Curated edge-native world models where sacred geometry, biophysical ODEs, and discrete quantum walks collide on local silicon. • 1 item • Updated Sep 6 • 2