IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license ibm-research • 10 days ago • 58
Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents quao627 • 4 days ago • 15
Same bytes, closer to the original: two lines of AutoRound we had wrong FINAL-Bench • 5 days ago • 12
OpenRouter Leaderboard: 425 Models by Price, Measured Speed and Korean Quality ginigen-ai • 3 days ago • 12
Trained 210M text-to-image model from scratch on one GPU: what actually mattered ivanmikhnenkov • 10 days ago • 9
DAVIDAU DELETED MY POST AND BANNED ME FOR ASKING ABOUT BENCHMARKS — HERE IS THE FULL ANALYSIS (9B + 27B + 390 MODELS) DedeProGames • Aug 11 • 23
BananaMind 2 Pro: We've (almost) matched SmolLM2 at 20x fewer tokens... Trained On a 5070 Ti Banaxi-Tech • 1 day ago • 5
I love speed. We all love speed. But what happens when the speed is slowing you down? darkc0de • 6 days ago • 3
IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license ibm-research • 10 days ago • 58
Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents quao627 • 4 days ago • 15
Same bytes, closer to the original: two lines of AutoRound we had wrong FINAL-Bench • 5 days ago • 12
OpenRouter Leaderboard: 425 Models by Price, Measured Speed and Korean Quality ginigen-ai • 3 days ago • 12
Trained 210M text-to-image model from scratch on one GPU: what actually mattered ivanmikhnenkov • 10 days ago • 9
DAVIDAU DELETED MY POST AND BANNED ME FOR ASKING ABOUT BENCHMARKS — HERE IS THE FULL ANALYSIS (9B + 27B + 390 MODELS) DedeProGames • Aug 11 • 23
BananaMind 2 Pro: We've (almost) matched SmolLM2 at 20x fewer tokens... Trained On a 5070 Ti Banaxi-Tech • 1 day ago • 5
I love speed. We all love speed. But what happens when the speed is slowing you down? darkc0de • 6 days ago • 3