13:08 Tutorials6 months ago Gemma 4 12B QAT + MTP on llama.cpp Locally – Twice the Speed, Same Quality? This video by Fahd Mirza walks through running Google's newly released Gemma 4 12B QAT (Quantization-Aware Training) model alongside... 0 comments 3K views
06:01 Coding & Builds6 months ago Run Google’s newest 12B AI on a phone? Yes, it’s possible! The Alphastack channel walks through a custom cross-platform app that runs Google's Gemma 4 12B multimodal model entirely on-device —... 0 comments 218 views
09:07 Tutorials6 months ago DwarfStar: Run DeepSeek V4 Locally with DS4 at 34 tok/s Fahd Mirza covers DwarfStar, a brand-new inference engine built specifically for DeepSeek V4 Flash (DS4) by the creator of Radius. Un... 0 comments 2.8K views
32:57 Tutorials6 months ago Unsloth Studio is insane… fine-tune any AI model locally Unsloth Studio is a free, open-source desktop application that brings LLM fine-tuning to consumer hardware — and this video by David... 0 comments 8.4K views
10:06 Coding & Builds6 months ago DFlash Leaves Qwen Territory – Gemma 4 31B Now Runs 5x Faster with Speculative Decoding Fahd Mirza demonstrates the first end-to-end deployment of Llama Box DFlash with Google's Gemma 4 31B model, following the merge of P... 0 comments 3.6K views
08:53 Reviews & Comparisons6 months ago $400 Chinese GPU That Wants to Dethrone NVIDIA Fahd Mirza takes a close look at the Lision LX7G 100, a roughly $485 consumer GPU developed entirely in China without CUDA, AMD archi... 0 comments 3.2K views
29:59 Interviews6 months ago ⚡️ Google’s Open AI Strategy — Omar Sanseviero, Google DeepMind In this Latent Space podcast interview, Omar Sanseviero from Google DeepMind walks through the technical decisions and strategic thin... 0 comments 490 views
08:11 News & Opinion6 months ago Weekly AI Recap – Qwen3.7, MTP in llama.cpp, SANA and More | May 2026 Fahd Mirza's weekly AI recap for May 2026 covers the most consequential model releases, infrastructure updates, and industry deals of... 0 comments 1K views
09:01 Tutorials6 months ago Llama.cpp Router Mode: Switch Models Instantly: Hands-on Local Demo Fahd Mirza demonstrates llama.cpp's built-in router mode, a native feature that enables instant model hot-swapping without third-part... 0 comments 2.4K views
10:48 Tutorials6 months ago LM Studio Just Got MTP — Qwen3.6-27B Runs 63% Faster with One Toggle Fahd Mirza demonstrates how to enable Multi-Token Prediction (MTP) speculative decoding in LM Studio's new beta release (version 0.4.... 0 comments 6K views