09:52
Luce Megakernel — 25x Faster Than PyTorch on a Single GPU – Test Locally
A new open-source project called Luce Megakernel is challenging long-held assumptions about GPU inference efficiency by fusing all 24...
Sort by: Newest Items
There are 85 items in this page
19:11
Your Agent Can Now Train Models — Merve Noyan, Hugging Face
Merve Noyan from the Hugging Face open-source team delivers a broad survey of the current open-model landscape alongside several firs...
22:54
This 100% uncensored AI model is insane… let’s run it
David Ondrej walks through the rationale, setup, and practical use of uncensored large language models running locally in 2026. The v...
11:12
Qwen3.6 27B Gets 20% Faster with MTP and llama.cpp Locally
Fahd Mirza demonstrates how to enable multi-token prediction (MTP) on Qwen3.6 27B using ik_llama.cpp — a community fork of the popula...
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...
32:36
RTX 5090, Mac Studio, or DGX Spark? I tried all three.
Nate B Jones tests the RTX 5090, Apple Mac Studio, and NVIDIA DGX Spark as personal AI computing platforms, but the video is as much...
09:01
Running a 27B model at 130 tokens sec on a single GPU Locally with Luce DFlash
LlamaDeFlash is a custom inference engine built from scratch in C++ and CUDA — no vLLM, no llama.cpp, no Python in the critical path...
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...
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...
15:26
Gemma, DeepMind’s Family of Open Models — Omar Sanseviero, Google DeepMind
Omar Sanseviero, a researcher at Google DeepMind, delivers the first public conference talk on Gemma 4 just one week after its releas...