Video
Fahd Mirza
2026-06-27
DSpark - DeepSeek Just Made Inference 85% Faster
Demonstrates running DeepSeek models using DSpark, a method described as making inference significantly faster.
Videos
Videos about AI and LLM
Find videos about LLM models, hardware, runtimes, benchmarks and practical AI workflows.
1083 videos found
Showing 901-950
Video
AI with Eric
2026-06-27
This Qwen3 Fine-Tune Beat Qwen3.6-27B? Ornith-1.0-35B Tested
Tests Ornith-1.0-35B against Qwen3.6-27B using a Splunk Cyber CTF question and an agentic Pi extension build judged by Opus 4.8.
Video
Fahd Mirza
2026-06-27
Qwythos 9B: When You Train a Small Model on Claude Traces: Run Locally
Locally installs and tests the Qwythos-9B-Claude-Mythos-5-1M-GGUF full-parameter reasoning model on Claude Mythos and Claude Fable datasets.
Video
xCreate
2026-06-27
NEW Open Source Qwen? BEATS GLM 5.2 & Claude? 🧐 Ornith 397B TESTED
Ornith-1.0-397B is tested using Inferencer App v2.0.6 on M3 Ultra 512GB, reportedly topping GLM 5.2 and Claude Opus in benchmarks.
Video
Fahd Mirza
2026-06-26
OpenJarvis + Ollama: Local AI Agent That Tracks Every Watt
Locally installs and tests OpenJarvis with Ollama, an open-source framework for building personal AI agents running on local hardware.
Video
Luke's Dev Lab
2026-06-26
North Mini Code vs Qwen 3.6 35B A3B coding - 16GB Local LLM setup
Cohere Labs North Mini and Qwen 3.6 35B A3B are tested via 2D Driving Game, Fake Desktop, and Slime Maze tasks on a local system with 16GB VRAM and 32GB DDR4 RAM.
Video
Fahd Mirza
2026-06-26
Hermes Agent /learn — Teach Your AI Agent Anything
Demonstrates using Hermes Agent's /learn command to convert URLs, codebases, or conversations into reusable AI skills within seconds.
Video
KGP Talkie
2026-06-26
Connect Hermes Agent to Discord: Control Your AI Agent From Your Phone (2026)
Demonstrates connecting the Hermes agent to a Discord server via a bot created through the Discord Developer Portal using the hermes gateway setup command.
Video
Fahd Mirza
2026-06-25
Ornith 1.0 9B: Self-Improving Model for Agentic Coding - Run Locally
Locally installs and tests Ornith-1.0, a self-improving family of open-source models for agentic coding.
Video
xCreate
2026-06-25
How much FASTER is GLM 5.2 with MTP 💪 | Local AI TEST
Tests the speed impact of Multi-Token Prediction on GLM 5.2 using Inferencer App v2.0.6 on an M3 Ultra 512GB system.
Video
Execute Automation
2026-06-25
How I Built a Custom QA LLM Using Unsloth, LoRA & Apple MLX — Complete Beginner Course
Demonstrates fine-tuning Large Language Models using Unsloth, LoRA and Apple MLX, covering techniques from basics to methods used by DeepSeek R1.
Video
Fahd Mirza
2026-06-25
Qwen-AgentWorld: One AI Model That Simulates 7 Different Environments
Locally installed and tested Qwen-AgentWorld, identified as the first language world model covering seven agent interaction domains within a single model architecture.
Video
Donato Capitella
2026-06-25
GLM 5.2 on Dual Strix Halo (256GB): Worth it?
Evaluates GLM 5.2 on dual Strix Halo via UD-IQ2_M quantization, measuring token generation/prompt processing speeds against DeepSeek V4 Flash and testing coding capability with SWE Bench verified mini
Video
Cole Medin
2026-06-25
Google Just Dropped a Masterclass on Agentic Engineering (It's SO Good)
Breaks down Google's whitepaper "The New SDLC With Vibe Coding" on agentic engineering, highlighting the Agent equals Model plus Harness framework, context engineering, and token economics.
Video
Matt Wolfe
2026-06-24
9 Free AI Skills That Feel Like Cheat Codes
Demonstrates installing and comparing nine free skills and plugins for Claude Code, Codex, Cursor, OpenClaw, Hermes, VS Code, and GitHub Copilot, including GStack, Stop Slop, Graphify, Understand Anyt
Video
Token Chaser
2026-06-24
Qwythos 9B vs Qwen3.5 9B | 16Gb vRAM Head-to-Head
A three-phase web coding challenge evaluates Qwen3.5 9B and Qwythos 9B on creating an iPhone-style UI, functional apps, and a launch site within a browser environment.
Video
Fahd Mirza
2026-06-24
Mistral OCR 4 Is Built Different - 170 Languages, and Does It Beats Them All?
Thoroughly tests the Mistral OCR 4 model.
Video
Luke's Dev Lab
2026-06-24
Cohere Labs North Mini Code 1.0 Tested - 16GB Local LLM setup
North Mini Code 1.0 is evaluated via Performance, Memory, Agency, OpenAI Human Eval, Sand Physics, and Dungeon Crawler tests on a system with 16GB VRAM and 32GB DDR4 RAM.
Video
Fahd Mirza
2026-06-24
Unlimited OCR from Baidu: One-shot Long-horizon Parsing: Run Locally
Locally installs and tests baidu/Unlimited-OCR using resources from Hugging Face.
Video
AI with Eric
2026-06-24
Is Flux Dead? Krea 2 Turbo Local AI Image Generation Goes HARD
Tests Krea-2-Turbo and Krea-2-Raw locally via SGLang for text-to-image quality and speed against Stable Diffusion and Flux-style models.
Video
Fahd Mirza
2026-06-23
Microsoft FastContext: The 4B Bug Hunter: Run Locally
Locally installs and tests Microsoft FastContext-1.0-4B-SFT, a lightweight repository-exploration subagent designed for LLM coding agents.
Video
Bijan Bowen
2026-06-23
Sakana Fugu Hands-On Test – Does THIS Really Beat Fable 5?
Tests Sakana Fugu across browser workflows, subway scenes, FPS games, C++, multimodal coding, frontend design, and flight simulation.
Video
WorldofAI
2026-06-23
Sakana Fugu Ultra BEATS Fable 5 & GPT-5.5? (Fully Tested)
Tests Sakana Fugu Ultra via real-world coding, reasoning, and agentic evaluations against Fable 5, GPT-5.5, Opus 4.8, and GLM 5.2 using LiveCodeBench, SWE-Bench, and GPQA.
Video
xCreate
2026-06-23
Better than Mac Mini for Local AI OpenClaw? 🧐 | TerraMaster F4-425 Pro Review
Evaluates the TerraMaster F4-425 Pro NAS running native OpenClaw and Inferencer for Sovereign AI agents, featuring demonstrations of 3D platform and racing games alongside comparisons of Fable, GLM an
Video
KGP Talkie
2026-06-23
Hermes vs OpenClaw: Which AI Agent Is Better?
Demonstrates installing Hermes Agent on Windows with a free OpenRouter API key, then performs file copying via terminal and parallel sub-agent research on the Anthropic IPO using zero-cost models.
Video
Fahd Mirza
2026-06-23
PixelRAG Locally: RAG That Reads Screenshots Instead of Text
Locally installs PixelRAG and performs an end-to-end test using screenshots instead of text.
Video
Fahd Mirza
2026-06-22
SkillOpt: Microsoft's New Way to 'Train' AI Agents: Run Locally
Microsoft SkillOpt is installed locally and tested.
Video
Luke's Dev Lab
2026-06-22
Gemma4 12B Coder - Composer 2.5 × Fable 5 v2 vs base - 16GB Local LLM setup
Tests Gemma 4 12B finetune with Fable 5 and Composer 2.5 against base via Q4_K_M quant on 16GB VRAM using Performance, Memory, Agency, OpenAI Human Eval, Sand Physics and Dungeon Crawler benchmarks.
Video
Fahd Mirza
2026-06-22
GLM-5.2 vs MiniMax-M3 vs Qwen3.7-Max — 3 Coding Tests, One Winner
GLM 5.2, Qwen 3.7, and MiniMax m3 are compared on real coding tasks performed live within the Hermes Agent environment.
Video
AI with Eric
2026-06-22
I Was WRONG About GLM-5.2: Opus-Level AI at Home?
Tests Z.AI GLM-5.2 in Claude Code UltraCode Mode against Claude Opus, GPT-5.5, and frontier-model workflows for real technical planning and implementation work.
Video
Fahd Mirza
2026-06-21
Ponytail + OpenClaw + Ollama: 20K Tokens to 2K Tokens - Don't Overbuild
Locally installs Ponytail with Ollama and OpenClaw and tests the setup.
Video
Alex Ziskind
2026-06-21
I Thought Local AI Video Was Good
Claude Code connects to Higgsfield MCP for programmatic AI video, image, and audio generation.
Video
Fahd Mirza
2026-06-21
Qwen3.6 (REAP 90pct GGUF): The Brain-Damaged Model
Locally installs and tests Qwen3.6-35B-A3B-REAP-90pct-GGUF, described as a meme model.
Video
Codacus
2026-06-21
Everything That Actually Matters for Local AI
Explains local LLM deployment via VRAM sizing, KV cache management, llama.cpp tensor overrides, GGUF/Q4_K_M/IQ quantization, and MoE offloading to run models like gpt-oss 120B on constrained hardware.
Video
xCreate
2026-06-21
Can a Local AI Cluster DESTROY Claude Fable? 🤯 (GLM 5.2 + Kimi K.27)
Compares local models GLM 5.2 and Kimi K2.7 Code against cloud options Gemini Pro, Claude Sonnet, and Claude Fable using Inferencer App on Mac Studio M3 Ultra 512GB across game development tasks.
Video
Fahd Mirza
2026-06-20
GLM 5.2 - Why Everyone is Loving It? And How to Run It Locally
Evaluates why the open-source community favors GLM-5.2, identifies its shortcomings, and specifies the hardware required for local execution.
Video
Luke's Dev Lab
2026-06-20
Qwable 3.6 27B tested - 16GB Local LLM setup
Mia-AiLab Qwable-3.6-27b is evaluated via 2D Driving Game, Sand Physics, Dungeon Crawler, and OpenAI Human Eval (kinda) on a system with 16GB VRAM and 32GB DDR4 RAM.
Video
Bijan Bowen
2026-06-20
North Mini Code First Test – Cohere’s LOCAL Agentic Coding Model!
Evaluates North Mini Code through browser workflows, scene generation, 3D printer simulation, C++ game generation, frontend design, flight simulation, roleplay, and website generation.
Video
KGP Talkie
2026-06-20
Hermes Agent Setup with Free AI API - Full Tutorial (2026)
Installs Hermes Agent on Windows, connects OpenRouter for free APIs, selects Llama M.1 and Nemotron models, tests computer control, and runs parallel sub-agents for research.
Video
Fahd Mirza
2026-06-20
Qwen3.6 27B (Pi-Reasoning GGUF) - Fine-Tuned for Local Heavy AI Agent
Locally installs Qwen3.6-27B-MTP-pi-reasoning-GGUF with hermes agent.
Video
Fahd Mirza
2026-06-19
OpenDataLoader PDF: Open-Source PDF Parser for RAG Pipelines (Local, No GPU)
Installs and tests opendataloader-pdf, an open-source PDF parser designed for generating AI-ready data within Retrieval-Augmented Generation pipelines.
Video
Zero to MVP
2026-06-19
GLM 5.2 vs Kimi K2.7 Code — Which Is Better for Coding?
Tests GLM 5.2 and Kimi 2.7 Coder using Ollama Cloud and Pi agent on sorting algorithm visualizers and Rust desktop file apps via running and debugging.
Video
WorldofAI
2026-06-19
GLM 5.2: NEW Opensource KING IS BEATING GPT-5.5 & Opus 4.8! (Fully Tested)
Tests GLM-5.2 against GPT-5.5, Claude Opus 4.8, and Gemini 3.1 Pro using Design Arena, DeepSWE, Frontier SWE, Terminal-Bench, and SWE-bench Pro for coding, agentic workflows, and frontend tasks.
Video
KGP Talkie
2026-06-19
Free OpenClaw Slack Setup - Full Setup Guide
Demonstrates configuring OpenClaw with Slack via openclaw configure, creating a Slack app with JSON manifest, obtaining bot and app-level tokens, enabling channel access, and restarting the gateway fo
Video
Fahd Mirza
2026-06-19
GLM-5.2 vs Claude Opus 4.8: Two AI Models, the Same Brutal Tests
GLM-5.2 and Claude Opus 4.8 are compared on real coding tasks within the Hermes Agent environment across multiple tests.
Video
Fahd Mirza
2026-06-18
New 225B Coding Model Laguna M.1 - Honest Test (Bugs + Creative Code)
Tests the 225B total parameter Mixture-of-Experts model Laguna M.1 for agentic coding and long-horizon work.
Video
Token Chaser
2026-06-18
Fusion vs Qwen3.6 27B | Head to Head Coding Battle
Compares OpenRouter Fusion and Qwen3.6 27B building the same web app from scratch on fresh Linux VPSes across phased builds to evaluate planning, adaptation, and shipping capabilities.
Video
Alex Ziskind
2026-06-18
This Is What Happens When You CRUSH An AI Video Model
Local AI video models are quantized to 4-bit and lower precision levels to evaluate degradation effects, with charts and results published at quant-degrade.pages.dev.
Video
Bijan Bowen
2026-06-18
Liquid LFM2.5-8B First Test – An On-Device MoE Model!
Tests Liquid LFM2.5-8B-A1B on browser workflows, website generation, roleplay, general knowledge, Python coding, and tool calling in real-world scenarios.
Video
Luke's Dev Lab
2026-06-18
Qwopus 3.6 27B Coder MTP coding challenges - 16GB Local LLM setup
Evaluates Jackrong's Qwopus 3.6 27B Coder MTP against base Qwen using OpenAI HumanEval, 2D Driving Game, Sand Physics, and Dungeon Crawler tests on a 16GB VRAM system.