11:39
Poolside Laguna XS.2: New Open Weight Coding Model Tested Locally with vLLM
Poolside AI has released two new open-weight coding models: Laguna M.1 (2–5 billion parameters) and Laguna XS.2, a 33-billion-paramet...
Sort by: Newest Items
There are 179 items in this page
12:24
Mistral Medium 3.5 128B: Built for Long Stretches on Coding: Full Testing
Fahd Mirza puts Mistral Medium 3.5 through hands-on testing in this evaluation of the newly released 128-billion-parameter dense mode...
18:10
NVIDIA Nemotron 3 Nano Omni — See, Hear & Read Everything Locally
NVIDIA's Nemotron 3 Nano Omni is a newly released multimodal model capable of processing video, audio, images, and long-form text sim...
12:57
Agents-CLI: Google Open-Sourced Enterprise Agent Playbook: Hands-on Demo
Fahd Mirza provides a step-by-step demonstration of Google's newly released Agents CLI, an open-source tool designed to dramatically...
15:18
MiMo-V2.5-Pro: Better Than DeepSeek V4? Deep-Dive with Testing
Xiaomi's MiMo V2.5 Pro enters the frontier open-source model conversation with this hands-on deep dive from Fahd Mirza. The 1 trillio...
14:53
This Mutant AI Model Should Not Exist: Qwopus-GLM-18B-Merged Locally
Fahd Mirza walks through the creation and live testing of Qwopus-GLM-18B-Merged, a community-built model that stitches together two s...
08:41
Google Released TIPSv2 – Beats Others at Their Own Game – Run Locally
Fahd Mirza walks through a local deployment of Google DeepMind's TIPSv2 (Transferable Image-text Pretraining with Spatial awareness),...
10:52
DeepSeek V4 Pro + OpenClaw: Full-Stack Agentic Coding on a Real Broken App
DeepSeek V4 Pro is a 1.6-trillion-parameter mixture-of-experts model with 49 billion activated parameters and a 1-million-token conte...
09:08
Open WebUI Desktop App – Install on Linux, Windows & Mac
Open WebUI has shipped its first native desktop application for Windows, macOS, and Linux, and Fahd Mirza walks through the complete...
11:47
Hy3 Preview: Tencent’s Most Powerful AI Model Yet — Full Test
Fahd Mirza tests Tencent's Hy3 Preview, a 295 billion parameter mixture-of-experts model that activates only 21 billion parameters at...