13:37
Zaya1 8B – Intelligence Efficiency by Zyphra – Run Locally
Zyphra, a San Francisco AI lab known for earlier releases like Zonos and ZR1, has returned with Zaya 1 (Zia) 8B — an open-source mixt...
Sort by: Newest Items
There are 95 items in this page
12:39
IBM Granite 4.1 8B – Open Source AI That Actually Surprised Me: Run Locally
Fahd Mirza covers the release of IBM's Granite 4.1 model family — available in 3B, 8B, and 30B parameter sizes — under a fully permis...
15:31
PFlash + Qwen3.6-27B-DFlash: 10x Faster Prefill on a Single GPU: Run Locally
Fahd Mirza builds and benchmarks PFlash, a prefill acceleration tool that dramatically reduces the blank-screen wait time when feedin...
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...
09:14
MemPalace with Ollama – Free Local AI Memory That Never Forgets
Fahd Mirza demonstrates MemPalace, a free open-source local memory system for AI that scored 96.6% on the LongMemEval benchmark — rep...
20:40
Run ACE-Step 1.5-XL Locally: Generate Songs with Music in Any Language for Free
Fahd Mirza walks through a local installation of ACE-Step 1.5-XL Turbo, an open-source music generation model whose developers claim...
08:08
Mobile Agent with GUI-OWL: AI That Controls Any Screen Like a Human: Run Locally
GUI-OWL 1.5 is a native multimodal GUI agent from Alibaba's mPLUG team, built on top of Qwen 3 VL, capable of controlling desktops, m...
08:19
Marco-Nano & Marco-Mini: Alibaba’s Insane Sparse MoE Models: Run Locally
Fahd Mirza installs and tests two new sparse mixture-of-experts models from Alibaba's AIDC AI division — Marco-Nano Instruct and Marc...
08:48
Gemma 4 Uncensored: Run with Ollama Locally for AI Safety Research
Fahd Mirza demonstrates how to run Gemma 4 E2B Uncensored — a modified version of Google's Gemma 4 2B model — locally using Ollama on...
10:08
Microsoft’s Harrier: The Most Multilingual Embedding Model You Haven’t Tried Yet
Microsoft has released Harrier, a family of three multilingual text embedding models that makes an unconventional architectural bet:...