Video
Fahd Mirza
2026-07-31
Whale Wokeup: DeepSeek V4-Flash Is Out of Preview — And It's Brutal
Tests DeepSeek-V4-Flash-0731, the official GA build.
Videos
Videos about AI and LLM
Find videos about LLM models, hardware, runtimes, benchmarks and practical AI workflows.
810 videos found
Showing 401-450
Video
WorldofAI
2026-07-31
DeepSeek V4 Flash Is OUT, OpenAI "mewthree" + GPT-5.6 Price/Speed Update, Qwen 3.8 Kinsley, & More!
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.
Video
Fahd Mirza
2026-07-31
MiniMax H3: Hands-On with the New Open-Weights AI Video Model
Tests MiniMax Hailuo H3, described as a general-purpose multimodal generation model.
Video
Fahd Mirza
2026-07-30
Inkling-Small Isn't Small At All: Let's Test this 276B Model
Tests Inkling-Small, a general-purpose multimodal model accepting text, image and audio inputs to generate text outputs.
Video
Alex Ziskind
2026-07-30
This was a data center a year ago… Now it's on my desk
Tests how many AI agents the ASUS ExpertCenter Pro ET900N G3 can run using its 748GB unified memory, 400Gb networking, and 1400 watt superchip.
Video
No place like localhost
2026-07-30
Multi-lingual AI voice cloning
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.
Video
Bijan Bowen
2026-07-30
GPT-5.6 Sol & Fable 5 – Game Vibe Coding With Abacus AI!
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
Video
Execute Automation
2026-07-30
Can a Mac Mini M4 16GB Run a 27B Model? Bonsai 27B Tested vs Qwen3.5 9B
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.
Video
Fahd Mirza
2026-07-30
Herdr: Run Multiple AI Coding Agents in Parallel from Your Terminal
Locally installs and tests Herdr, an agent multiplexer that runs multiple AI coding agents in parallel from the terminal.
Video
WorldofAI
2026-07-30
How to Build Claude Powered Agent Teams That Automate Your Life For FREE!
Demonstrates structuring Claude-powered agent teams using Hyperagent, assigning specific roles, creating reusable skills and memories, and building continuous business workflows.
Video
Cole Medin
2026-07-30
The Ultimate Knowledge Base: Bring YouTube Into Your AI Second Brain
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
Video
Fahd Mirza
2026-07-29
How to Run Kimi K3 Locally (3 Ways)
Demonstrates three methods for running Kimi K3 locally, referencing Inferact/Kimi-K3-DSpark from Hugging Face.
Video
Zero to MVP
2026-07-29
Gemma 4 12B Coder Tested: Where Small Local Models Break
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.
Video
Luke's Dev Lab
2026-07-29
Qwen 3.6 27B Fable Fusion 711 tested vs Base Qwen 27B - 16GB Local LLM setup
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
Video
Fahd Mirza
2026-07-29
Microsoft Fara1.5 27B: Local Install + Real Browser Automation Demo
Installs and tests Fara1.5-27B, a multimodal computer use agent for web browsers from Microsoft Research AI Frontiers.
Video
AI with Eric
2026-07-28
Laguna S-2.1 vs M.1 vs Qwen3.6-27B: Which Coding Model Wins?
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
Video
Fahd Mirza
2026-07-28
AMD Releases First Ever AI model: Instella-MoE-16B-A3B-Think
Trained from scratch on AMD Instinct MI300X and MI325X GPUs using AMD's Primus framework, featuring Gated Multi-head Latent Attention and FarSkip-Collective.
Video
xCreate
2026-07-28
Can Skywork AI write my PhD and make me Dad of the Year? 🤔
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.
Video
No place like localhost
2026-07-28
LLM Battle 3 - Qwen 3.6 27B vs Gemma 4 31B
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.
Video
Bijan Bowen
2026-07-28
Ling 3.0 Flash First Test – A Surprisingly GOOD Coding Model!
Tests Ling 3.0 Flash performance on browser OS, C++ games, FPS, frontend, 3D CAD models, city timelines, and a C++ racing game.
Video
Fahd Mirza
2026-07-28
Inflect Micro v2 - A Complete Voice AI Under 10M Parameters on CPU
Installs and tests Inflect-Micro-v2, a fixed-voice English TTS featuring deterministic seeds, long-text handling, and CPU operation.
Video
Fahd Mirza
2026-07-27
Microsoft Mage-Flow: Image Generation and Editing Locally
Mage-Flow is a 4B-scale generative stack for efficient text-to-image generation and instruction-based image editing.
Video
xCreate
2026-07-27
Ultimate AI? Fable 5 vs Opus 5 vs GPT 5.6 vs GLM 5.2 (Local AI)
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.
Video
No place like localhost
2026-07-27
Building a Star Trek chat app with AI voice cloning
Builds TalkWithMe, a local AI group chat app using configurable personas wired to a custom dots.tts REST server for AI voice cloning.
Video
Luke's Dev Lab
2026-07-27
Laguna XS 2.1 33B A3B tested vs Qwen 35B A3B - 16GB Local LLM setup
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.
Video
Execute Automation
2026-07-27
LM Studio Bionic Explained — The Agentic AI Tool for Open Models (Is It Worth It?)
Explains LM Studio Bionic, an agentic AI tool for open models, detailing its functionality and differences from LM Studio and other agentic tools.
Video
WorldofAI
2026-07-27
Turning Claude Fable 5 Into The Ultimate Second Brain!
Demonstrates connecting Claude Fable 5 with Cognee to give Claude Code persistent long-term memory for retrieving project knowledge across sessions.
Video
Fahd Mirza
2026-07-27
DeepSeek V4 Flash Fully Local — 32 tok/s on a Single Chip
Runs the 284B parameter DeepSeek V4 Flash model locally on an AMD Ryzen AI MAX+ 395 with 128GB unified memory using the Lucebox inference engine with DSpark speculative decoding.
Video
Unbiased Bob
2026-07-27
Evaluating ~3-4B parameter LLMs. Nanbeige/Qwen/LocoOperator/Llama/Opus finetunes.
Qwen 3.5 4b remains the best 4 billion parameter model among Nanbeige, Qwen, LocoOperator, Llama and Opus finetunes.
Video
Codacus
2026-07-27
I Ran a 118B Model on My Old 3060. Here’s What Happened.
Compares Laguna S 2.1 and Qwen 3.6 35B-A3B on an RTX 3060 using llama.cpp, evaluating debugging accuracy and animation generation tasks via manual testing.
Video
AI Search
2026-07-27
Claude Opus 5 is a freak
Tests Claude Opus 5 via image to 3D, financial videos, Luma Agents, Blender, music, FROG TEST, cancer identification, deep research, specs, costs, benchmarks and guardrails.
Video
AI with Eric
2026-07-26
How I Run Multiple Coding Agents From One Claude Code Session (Firstmate + Herdr)
Tests Firstmate coordinating Claude Code, Codex CLI, Pi, OpenCode and Grok Build via Herdr, managing parallel tasks, Git worktrees and worker recovery.
Video
Alex Ziskind
2026-07-26
AMD Says 2 Ryzen AI Halos Can Run a 400B Model... I Tested It
Tests whether two AMD Ryzen AI Halo systems can run a 400B parameter model, evaluating local large language model inference performance on consumer hardware.
Video
WorldofAI
2026-07-26
LingBot-World 2.0: You can LIVE and CONTROL an AI WORLD!
Demonstrates LingBot-World 2.0 using causal pretraining, MoBA attention, and agents for real-time interactive world generation at 720p 60fps via 14B and 1.3B models.
Video
Fahd Mirza
2026-07-26
Run Alibaba OvisOCR2 Locally: First Model to Ever Beat the Pipeline-Based Methods
Tests OvisOCR2, a compact 0.8B end-to-end model for page-level document parsing.
Video
AI Search
2026-07-26
Claude Opus 5, GPT 6 hack, Flux 3, new Gemini, quantum breakthrough, new Qwen: AI NEWS
Covers Claude Opus 5, Gemini 3.6, Qwen 3.8, Flux 3, Qwen Image 3, Laguna S2.1, Mage Flow, ShotPlan, Homie, OpenAI hack, ChatGPT Health, GLM with vision, GPT live voice, Google quantum breakthrough, Na
Video
xCreate
2026-07-26
GLM 5.2 Coding LoRA BEATS Kimi K3 & Claude?! 🤯 | Local AI In-Depth REVIEW
Evaluates Inferencer Labs' Macaron-V1 LoRA for GLM-5.2 on an M3 Ultra 512GB using music generation, human anatomy, game development tasks and photorealistic face creation tests.
Video
Fahd Mirza
2026-07-25
Solar Open 2 - An Agentic Model for Office Productivity
Tests Upstage’s 250B-A15B open-weight model for office productivity and document-intensive work.
Video
BridgeMind
2026-07-25
The biggest issue with Kimi right now is that it only outputs 21 tokens per second.
Kimi produces high-quality front-end website design output but suffers from slow generation speeds due to limited compute resources.
Video
Fahd Mirza
2026-07-25
Opus 5 is Here: Let's Compare it to Kimi K3 Hands-on
Compares Opus 5 with Kimi K3 on hard coding tasks.
Video
BridgeMind
2026-07-25
GPT 5.6 is hitting massive hallucination rates of 89%, 90%, and even 91%.
Compares hallucination rates of GPT 5.6, GPT 5.5, and GPT 5.6 Tera against Fable 5, Grok 4.5, Kimi K3, and Minimax, noting higher rates for GPT models.
Video
WorldofAI
2026-07-25
Claude Opus 5 Is THE GREATEST AI Model EVER?! Beats Fable & CHEAPER! (Fully Tested)
Tests Claude Opus 5 against Fable 5, GPT-5.6 Sol, and Kimi K3 via World of AI Bench, ARC-AGI-3, Artificial Analysis, coding, reasoning, and game dev demos.
Video
Bijan Bowen
2026-07-25
Claude Opus 5 Is INSANE – Is This the BEST Model Yet?
Evaluates Claude Opus 5 via browser OS tests, C++ skate game, frontend design, Subway FPS, UltraCode City Timeline, and Street Yeet game creation tasks.
Video
Execute Automation
2026-07-24
I Ran Laguna XS 2.1 Against Qwen3.6 on Apple Silicon... Here's What Happened
Compares Laguna XS 2.1 and Qwen3.6 on Apple Silicon via setup, speed, token throughput, response quality, reasoning, and tool-use accuracy for real agentic coding tasks.
Video
Fahd Mirza
2026-07-24
Beyond Qwen & DeepSeek: Testing Intern-S2-Preview-397B
Tests Intern-S2-Preview-397B, InternLM's most capable multimodal foundation model for scientific intelligence.
Video
BridgeMind
2026-07-24
Vibe Coding With Claude Opus 5
Evaluates Claude Opus 5 via BridgeBench V3 against Fable 5, GPT 5.6 SOL, Kimi K3, and Grok 4.5 using Claude Code, BridgeSpace multi-agent orchestration, and production bug fixes.
Video
Matt Wolfe
2026-07-24
AI News: Kimi K3 Has Big AI Labs Panicking!
Covers Kimi K3 launch, US sanctions threat against Chinese AI models, OpenAI Hugging Face security incident, Gemini 3.6 Flash models, Qwen3.8 open-weight release, ChatGPT health features, Claude voice
Video
xCreate
2026-07-24
Is FREE AI Text to Speech and Voice Cloning Finally Good? (Fish Audio)
Evaluates Fish Audio's Free for Devs AI Text to speech and voice cloning tools for their ability to generate realistic human emotion.
Video
Cole Medin
2026-07-24
Is Kimi K3 Really That Good?! (Don't Just Believe The Hype)
Evaluates Kimi K3 against Opus 4.8 and Kimi K2.7 on real engineering tasks using a custom benchmark suite scoring seven dimensions, revealing higher failure rates for complex tasks despite strong perf
Video
Bijan Bowen
2026-07-24
Poolside Laguna S2.1 First Test – A VERY Creative Local Model!
Tests Poolside Laguna S2.1 performance in browser workflows, C++ game creation, FPS development, creative writing, website design, fan fiction, 3D printer simulation, and frontend testing.