Videos
Find videos about LLM models, hardware, runtimes, benchmarks and practical AI workflows.
Sets up a local TTS server using dots.tts and Qwen3-TTS, then integrates both models into the TalkWithMe AI group chat application to compare their performance.
Tests Qwen3.8 Max across browser workflows, C++ game creation, 3D CAD modeling, cinematic games, frontend design, creative writing, and multimodal coding.
Evaluates KAT Coder V2.5 Dev against Qwen 3.6 35B A3B using performance, memory, agency, OpenAI Human Eval, Kanban, Sand Physics, Dungeon Crawler, Blender and Godot tests.
Tests Qwen 3.8-Max, described as the most capable model in the Qwen family to date.
Compares Seedance 2.5 and Minimax H3 across multimodal features, instruction following, sketch to animation, storyboard to commercial, UI motion graphics, music videos, language tests, specs and costs
Evaluates Elements Labs' Bionic for local, private coding and software engineering using open-weights models.
Evaluates local AI agent harnesses using an RTX 3060 and qwen36-35b-a3b-mtp, comparing OpenClaw and Hermes against a custom build with llama-server, Telegram integration, and n8n automations.
Locally installs and tests ARK-ASR-3B, a multilingual automatic speech recognition model hosted on Hugging Face under Audio8/ARK-ASR-3B.
Tests GPT-5.6 Luna performance on browser OS, C++ games, FPS dev, multimodal coding, 3D CAD models, watch frontends, Chrono City C++, HQ Street Yeet, and result improvement.
Tests HappyHorse 1.0 from Alibaba for generating cinematic frames.
Overview of Deepseek V4 Flash 0731, Seedance 2.5, Minimax H3, Kimi K3, Instella, Inkling Small, Prism, Wonder, Phi Zero, ID V2V, Crisper Whisper, Redesign, Ideogram object remover, Higgsfield, Gemini
Evaluates DeepSeek-V4-Flash-0731-MLX using Inferencer App v2.2.3 on M3 Ultra 512 GiB across local and cloud setups against GLM 5.2 benchmarks.
Compares MiniMax H3 against Google Gemini (Veo 3.1) and OpenAI's Sora 2 on cost, resolution, and generation quality using text, image, video, and audio inputs.
Tests DeepSeek-V4-Flash-0731 checkpoint for speed, coding quality, tool use, hallucinations and reliability, then compares results against Tencent HY3 and Qwen3.6-27B.
Installs and demonstrates using Obsidian with Ollama and hermes-agent for free hands-free note management.
Demonstrates a single-user DGX Station setup with 748GB of unified memory running GLM 5.2 in VSCode.
Voice features on ChatGPT and Claude enable hands-free building, editing, and iteration of interactive 3D designs, such as generating an Iron Man suit, scaling helmets, changing colors, and adding sol
Benchmarks DeepSeek V4 Flash against GPT-5.6 Luna, Kimi K3, GLM 5.2, and DeepSeek V4 Pro via WoAI Benchmark in coding, AI agents, frontend development, Three.js, game generation, and UI design.
Installs and tests Conversation Stenography locally using nethical6/conversation-steganography repository for private AI chats.
Covers Claude Opus 5 tests, Google Earth Nano Banana, Meta AI Agents, BUZZ, Grok Build Mode, Gemini features, Midjourney 8.2, Mirage Avatar X, HeyGen, LinkedIn AI button, Friend wearable, robot bans a
Tests DeepSeek V4 Flash on browser workflows, C++ games, FPS dev, frontend design, 3D CAD modeling, and the Steve’s PC Repair game test.
Demonstrates QVAC, an open-source local AI platform providing Whisper, embeddings, Qwen, and text-to-speech via a single npm install across multiple operating systems under Apache 2.0 license.
Evaluates Laguna S 2.1 118B A8B against its XS version using Performance, Memory, Agency, OpenAI Human Eval, Sand Physics, Kanban, Dungeon Crawler, Blender and Godot tests.
Tests DeepSeek-V4-Flash-0731, the official GA build.
Covers DeepSeek V4 Flash GA, OpenAI mewthree leak, GPT-5.6 price/speed updates, Qwen 3.8 Kinsley, MiniMax H3, Seedance 2.5, Gemini 3.5 Pro on LM Arena, Inkling-Small, and Gemini Robotics 2.
Tests MiniMax Hailuo H3, described as a general-purpose multimodal generation model.
Tests Inkling-Small, a general-purpose multimodal model accepting text, image and audio inputs to generate text outputs.
Tests how many AI agents the ASUS ExpertCenter Pro ET900N G3 can run using its 748GB unified memory, 400Gb networking, and 1400 watt superchip.
Clones non-English voices using AI and integrates them into configurable AI tutors within the TalkWithMe application to facilitate language skill practice through transcribed interactions.
Demonstrates building a playable game using GPT-5.6 Sol and Claude Fable 5 via Abacus AI, covering code generation, AI NPC setup, autonomous play testing, visual upgrades, and mobile control implement
Tests Bonsai 27B 1-bit quantized versus Qwen3.5 9B on a Mac Mini M4 with 16GB RAM during general chat and within the Pi Coding Agent workflow.
Locally installs and tests Herdr, an agent multiplexer that runs multiple AI coding agents in parallel from the terminal.
Demonstrates structuring Claude-powered agent teams using Hyperagent, assigning specific roles, creating reusable skills and memories, and building continuous business workflows.
Demonstrates converting YouTube transcripts into plain markdown knowledge bases compatible with Obsidian and Google OKF, featuring canonicalization logic and three Claude Code skills for automated cre
Demonstrates three methods for running Kimi K3 locally, referencing Inferact/Kimi-K3-DSpark from Hugging Face.
Tests Gemma 4 12B Coder locally on MacBook M4 Pro using Ollama and Pi agent via color palette generator, pixel art editor single prompts, and step-by-step development across 18 tasks.
Evaluates Fable Fusion 711 Uncensored Heretic NM DAU NEO MAX MTP versus Base Qwen 3.6 27B using Performance, Memory, Agency, OpenAI Human Eval, Kanban, Sand Physics, Dungeon Crawler, Blender and Godot
Installs and tests Fara1.5-27B, a multimodal computer use agent for web browsers from Microsoft Research AI Frontiers.
Tests Laguna S-2.1, M.1 and Qwen3.6-27B via Grok Build and OpenCode on a Pi goal extension and Splunk CTF, evaluating coding quality, agentic behavior, reasoning, tool use, instruction following, loop
Trained from scratch on AMD Instinct MI300X and MI325X GPUs using AMD's Primus framework, featuring Gated Multi-head Latent Attention and FarSkip-Collective.
Evaluates Skywork’s capabilities for deep research, advanced coding design, writing a PhD thesis, and creating educational games using Qwen-3.6 on Inferencer App with M4 Max 128GB hardware.
Gemma 4 31B and Qwen 3.6 27B are compared across multiple stages in a dense LLM model battle, featuring code reviews and unexpected plot twists leading to confusing results.
Tests Ling 3.0 Flash performance on browser OS, C++ games, FPS, frontend, 3D CAD models, city timelines, and a C++ racing game.
Installs and tests Inflect-Micro-v2, a fixed-voice English TTS featuring deterministic seeds, long-text handling, and CPU operation.
Mage-Flow is a 4B-scale generative stack for efficient text-to-image generation and instruction-based image editing.
Remakes GTA using Fable 5, Opus 5, GPT-5.6 Sol, and GLM 5.2 in a coding showdown comparing cloud giants against the open-weight champion.
Builds TalkWithMe, a local AI group chat app using configurable personas wired to a custom dots.tts REST server for AI voice cloning.
Evaluates Laguna XS 2.1 33B A3B against Qwen 3.6 35B A3B using Performance, Memory, Agency, OpenAI Human Eval, Sand Physics, Kanban, Dungeon Crawler, Blender, and Godot tests.
Explains LM Studio Bionic, an agentic AI tool for open models, detailing its functionality and differences from LM Studio and other agentic tools.
Demonstrates connecting Claude Fable 5 with Cognee to give Claude Code persistent long-term memory for retrieving project knowledge across sessions.