Videos
Find videos about LLM models, hardware, runtimes, benchmarks and practical AI workflows.
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
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.
Locally installs PixelRAG and performs an end-to-end test using screenshots instead of text.
Microsoft SkillOpt is installed locally and tested.
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.
GLM 5.2, Qwen 3.7, and MiniMax m3 are compared on real coding tasks performed live within the Hermes Agent environment.
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.
Locally installs Ponytail with Ollama and OpenClaw and tests the setup.
Claude Code connects to Higgsfield MCP for programmatic AI video, image, and audio generation.
Locally installs and tests Qwen3.6-35B-A3B-REAP-90pct-GGUF, described as a meme model.
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.
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.
Evaluates why the open-source community favors GLM-5.2, identifies its shortcomings, and specifies the hardware required for local execution.
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.
Evaluates North Mini Code through browser workflows, scene generation, 3D printer simulation, C++ game generation, frontend design, flight simulation, roleplay, and website generation.
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.
Locally installs Qwen3.6-27B-MTP-pi-reasoning-GGUF with hermes agent.
Installs and tests opendataloader-pdf, an open-source PDF parser designed for generating AI-ready data within Retrieval-Augmented Generation pipelines.
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.
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.
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
GLM-5.2 and Claude Opus 4.8 are compared on real coding tasks within the Hermes Agent environment across multiple tests.
Tests the 225B total parameter Mixture-of-Experts model Laguna M.1 for agentic coding and long-horizon work.
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.
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.
Tests Liquid LFM2.5-8B-A1B on browser workflows, website generation, roleplay, general knowledge, Python coding, and tool calling in real-world scenarios.
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.
Connects local Qwen3 35B via LM Studio with TestSprite MCP Server in VS Code to execute complete front-end automation tests entirely offline.
Locally installs dots.tts, a 2B-parameter fully continuous, end-to-end autoregressive text-to-speech system.
Evaluates GLM 5.2 performance using Inferencer App on M3 Ultra 512GB across photorealism, sound generation, 3D game dev, coding, maths, logic tests and AI safety.
Demonstrates building a TypeScript app running Pi (on Kimi) in a loop with an orchestrator spinning up parallel worker agents, storing runs in a database via the Agent Control Plane dashboard.
Locally installs LoopCoder-v2, a 7B instruction-tuned code model based on the Parallel Loop Transformer (PLT), sourced from Multilingual-Multimodal-NLP on Hugging Face.
Deploys DiffusionGemma 26B-A4B in NVFP4 with vLLM on RTX PRO 6000, benchmarking its 256-token parallel generation against standard Gemma 4 to demonstrate a 6.73x speedup.
Project Odysseus installation on M3 Mac using Ollama compares Gemma 3 12B and GPT 5.5 via deep research, brain memory, model comparison scoreboard, and image editor features.
Evaluates GLM 5.2 using Ollama Cloud and the Pi agent on three coding tests: a sorting algorithm, six algorithms with visualization, and a Hantavirus simulation in Rust, checking first-time compilatio
Demonstrates Luce KVFlash recalling a hidden fact within a 256K token novel-length prompt while paging most context off the GPU to conserve VRAM.
Tests Kimi K2.7 Code against Opus 4.8 Max, GPT-5.5, Fable 5, Qwen 3.7 Max, and Grok 4.3 using World of AI benchmark and a strange attractors coding test judged by GPT-5.5 Pro.
Reviews GLM 5.2 capabilities including digital earth, animation, 3D models, ray tracing, music composition, math animation, deep research and specs.
Installs and tests VibeThinker-3B, a 3B-parameter model from the VibeThinker series hosted on Hugging Face under WeiboAI.
Demonstrates setting up Hermes Agent by installing the software, connecting an LLM, verifying configuration using hermes doctor, executing a test session, and listing subsequent utility commands.
Evaluates OpenRouter Fusion against Claude Fable 5, GPT-5.5, and Claude Opus 4.8 using Browser OS, C++ Skate Game, Deep Research, and Frontend tests under quality and budget settings.
Qwen 3.6 27B non-MTP versus MTP variants are compared for performance, memory usage, agency capabilities, and coding skills on a system featuring 16GB VRAM and 32GB DDR4 RAM.
Demonstrates running DFlash with SGLang's Spec V2 overlap scheduler on Qwen3.6-27B, achieving 160 tok/s on a single H100 via installation, benchmarking, and performance measurement.
Locally installs gemma-4-12B-coder-fable5-composer2.5-v1-GGUF and tests it with hermes agent.
Qwopus3.6-27B-Coder-MTP and Qwen3.6-27B-MTP build a multi-phase LAN whiteboard app with drag-and-drop images, real-time chat, and advanced features on separate fresh VPSs.
Demonstrates DeepSeek V4 Flash inference on AMD Strix Halo via ds4 and ROCm/HIP, covering Q2/hybrid 4-bit configs under 128GB RAM, multi-node 4-bit clusters, and benchmarks against SWE Bench Mini.
Demonstrates Omnigent orchestrating Claude Code for implementation and Codex for code review within separate git worktrees, featuring multi-model debate and cross-device session continuity.
Demonstrates fitting a model's full 256K context on a small GPU using Luce KVFlash by keeping a tiny KV pool on the card and paging the rest to RAM.
Demonstrates creating autonomous Claude agents using Base44 Superagents to automate workflows like research, emails, and scheduling without code, hosting, or complex integrations.
Tests MiniMax M3 in Claude Code UltraCode Mode against GPT-5.5 via large codebase review, Pi /goal extension build-off, and Splunk cyber CTF challenge.