20:02 News & Opinion2 weeks ago Ripple 65B: A Chip Design Lab Just Beat Every US Open Model Sam Witteveen looks at Ripple 65B Preview, a new open-weight model from Recursive, a lab founded by the team behind Google's AlphaChi... 0 comments 6K views
13:44 Reviews & Comparisons4 weeks ago 100% Open Image Model Lets You Place Text With JSON Moss Image is a new 5-billion-parameter image generation model from Open Moss, the team behind Moss TTS, and it is released under the... 0 comments 3.5K views
14:56 Deep Dives1 month ago Xiaomi Just Showed Us What Million-Dollar RL Training Looks Like Xiaomi's latest open-weights language model, MiMo V2.6, is drawing attention not only for its performance but for how openly it was t... 0 comments 1.3K views
19:19 Coding & Builds2 months ago How to Build Things with Jev & OpenJevs Sam Witteveen builds a working model router using Jev, a "system one" decision model from TypeSafe AI that returns typed, probability... 0 comments 3.7K views
12:29 Reviews & Comparisons2 months ago Nex-N2.5 Mini: Multilingual, Multimodal, and Fully Agentic (Hands-On) Fahd Mirza provides a hands-on deployment walkthrough and capability test of Nex AGI's N2.5 Mini, the smaller model in the N2.5 agent... 0 comments 5.4K views
14:30 Benchmarks2 months ago MiniCPM5-2B: The Best Sub-Agent Model Yet? Sam Witteveen examines MiniCPM 2B (technically 2.5B), the latest small model from OpenBMB, which claims to beat 4B-class models on fu... 0 comments 4.4K views
01:28:12 Deep Dives3 months ago Deep dive on LLM Inference at Scale — Harshul Jain, Audible & Tanmay Sah, Independent AI Researcher Harshul Jain, senior software engineer at Audible and author of an open-source LLM inference handbook, teams up with AI researcher Ta... 0 comments 1.4K views
13:50 Reviews & Comparisons3 months ago MiniCPM5 2B: SOTA or Scam? Let’s Test Locally Fahd Mirza puts MiniCPM5 2B — the latest small model from ModelBench and Tsinghua University's NLP lab — through a gauntlet of real-w... 0 comments 5.2K views
11:30 Reviews & Comparisons3 months ago Spark X2.5 4B: What a 4B Model Can and Can’t Do Locally Fahd Mirza puts the newly released Spark X2.5 4B through a full local deployment and capability evaluation on a 48GB VRAM GPU. The mo... 0 comments 2.1K views
12:54 Coding & Builds3 months ago Qwen3.8-27B in 2-Bit Quant: Escha-W2 Build Locally without Loss Fahd Mirza demonstrates Escha-W2, Asha Labs' aggressively quantized version of Qwen3.8 27B, which compresses the model from 50GB at f... 0 comments 4.2K views