09:50
Qianfan-OCR: End-to-End OCR That Does Layout-as-Thought: Run Locally
Fahd Mirza demonstrates Qianfan-OCR (Chainfan OCR), a 4-billion parameter document intelligence model released by Baidu's Chainfan te...
Sort by: Newest Items
There are 95 items in this page
08:25
MiniCPM-SALA: Model That Makes 1M Token Context Actually Work
Fahd Mirza digs into MiniCPM-SALA, a new pre-trained model from the MiniCPM lab that introduces a hybrid attention architecture aimed...
13:29
Lossless-Claw: Infinite Memory for Your OpenClaw – Run Locally with Ollama and GLM
Fahd Mirza demonstrates Lossless-Claw, a community plugin for OpenClaw that solves a fundamental problem in long agentic sessions: th...
11:46
Run Unsloth Studio Locally – A Competitor to LMStudio?
Fahd Mirza provides a first-look installation and review of Unsloth Studio, a newly launched graphical interface from the Unsloth tea...
11:42
IBM Granite-4 1B Speech: Bidirectional Voice AI — Local Demo
Fahd Mirza walks through a full local installation and live test of IBM's Granite 4 1B Speech model, the newest addition to IBM's Gra...
08:53
NVIDIA NemoClaw + OpenShell: OpenClaw Agent in a Secure Sandbox – Local vLLM Setup
At GTC 2026, NVIDIA announced NemoClaw — an official security and sandboxing layer for OpenClaw agents, built in collaboration with O...
09:15
CLI-Anything + OpenClaw + Ollama: Turn Any Software Into an AI Agent Tool
Fahd Mirza introduces CLI-Anything, an open-source tool from HKUDS (the team behind ClawWork and ByteRover) that solves a practical p...
08:49
Ollama Official OpenClaw Integration: Full Local Setup Guide
Fahd Mirza covers Ollama's newly released official integration with OpenClaw, the open-source AI agent framework. Previously, connect...
08:36
OmniLottie: Generate Lottie Animations From Text, Image or Video — Locally
Fahd Mirza introduces and locally installs OmniLottie, described as the first AI model capable of generating complete Lottie animatio...
10:33
OmniCoder-9B Running Locally: I Tried to Break It With Real Engineering Tasks
Fahd Mirza puts OmniCoder-9B — a coding-focused model from Tesslr, fine-tuned on the Qwen3.5 9B hybrid architecture — through a hands...