Models283•09/18/2026, 10:47Qwen3.8-Omni-Flash Released: Multimodal Model with 1M Token Context2 min readRead
Models162•10/25/2026, 09:48DeepSeek-V4.1-Flash with 763B Parameters Can Run Locally on a 12GB GPU2 min readRead
GitHub685•06/23/2026, 10:00Qwythos-9B-Claude-Mythos-5 Released with a Context Window of Up to 1 Million Tokens.1 min readRead
Models422•08/22/2026, 09:15FreeToken: A New System for Running Large MoE Models on Regular PCs3 min readRead
Agents346•09/19/2026, 21:35NVIDIA Introduces SoL-Pi: Automatic AI Agent Harness Optimization2 min readRead
Vibe Coding373•09/22/2026, 12:02Jev Mod for Claude Code: Saving Tokens and Accelerating Skill Handling2 min readRead
Models347•09/14/2026, 10:19Recurrent Looped Transformer: A New Architectural Idea for AI2 min readRead
GitHub133•10/20/2026, 15:39DeepSeek releases DeepInfer, an open-source inference framework2 min readRead
Models153•10/16/2026, 15:50PrismML expands Bonsai 2 with three compact AI models for local agents3 min readRead