38:54
New Deepseek, human genome map, Navier Stokes, GPT finance, Suno v6, YuE2: AI NEWS
The AI Search channel's weekly roundup covers a dense slate of releases from the week of September 13, 2026. Leading the lineup is De...
Sort by: Newest Items
There are 11 items in this page
10:30
Ornith-1.5-9B: Great on Paper, Struggled in My Tests Locally
Fahd Mirza tests the Ornith 1.5 9B model — the smallest and densest member of the Ornith 1.5 family — on a single NVIDIA A100 with 80...
11:00
Ornith 1.0 35B in GGUF – Beats Models 10x Its Size – Run Locally
Fahd Mirza puts Ornith 1.0 35B through its paces in this hands-on local deployment walkthrough. Ornith is a mixture-of-experts model...
09:36
Qwen3.6 (REAP 90pct GGUF): The Brain-Damaged Model
Fahd Mirza takes a deep look at an aggressively pruned variant of Qwen 3.6 — a 35-billion-parameter mixture-of-experts model — compre...
09:42
Luce Spark: Run a 35B Model Under 16GB VRAM Locally
Fahd Mirza demonstrates LuceSpark, a memory management technique that allows a 35-billion-parameter mixture-of-experts model to run w...
12:47
Run Qwen3.6-27B Locally – Prioritizes Stability and Real-World Utility
Fahd Mirza walks through a complete local deployment of Qwen 3.6 27B, Alibaba's latest dense language model, on an Ubuntu server equi...
22:02
“But OpenClaw is expensive…”
Matthew Berman tackles one of the most common complaints about running AI agents at scale — cost — by presenting a hybrid architectur...
23:54
Gemma 4 26B A4B vs Qwen3.5 35B A3B: MoE Models Battle Locally
Fahd Mirza runs a direct head-to-head comparison of two mixture-of-experts models — Gemma 4 26B A4B (activating 3.8 billion parameter...
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...
11:51
OpenClaw + Chrome DevTools MCP: How to Give Your Local Agent Full Browser Control
This video by Fahd Mirza covers the integration of OpenClaw with Google Chrome using locally hosted Ollama models, specifically Qwen3...