Videos
Find videos about LLM models, hardware, runtimes, benchmarks and practical AI workflows.
Evaluates Qwen 3.8 27B against Qwen 3.6 27B on psim-blackbox using pi harness 0.79.3 across low, medium, and xhigh reasoning settings, showing performance varies significantly by mode.
Overview of Deepseek V4 0813, Qwen 3.8 variants, GLM 5.3, Grok 4.6, LTX 2.5, Gemini 3.7 Flash, GPT Ultrafast, JoyAI Video Edit, Scope, Index TTS 2.5, Minimax Music 3, Magi 2, Nemotron Lightning, and o
Locally installs and tests DeepSeek Harness (dsh), an open-source agent harness.
Evaluates Qwen 3.8-27B, a native multimodal dense model reading images and video, covering Unsloth quants, thinking-effort controls, NVFP4 Blackwell builds, and benchmarks against Opus 4.6 Max.
Side-by-side coding test using Claude Code on Ollama to generate Space Invaders, Breakout, and Tetris HTML canvas games with Qwen 3.8 27B, Muse Glimmer, and Gemma 4 on an RTX 5090.
Tests Qwen3.8-27B via live tool calling with Playwright MCP Server and migrating a .NET solution from .NET 8 to .NET 10, while examining Preserve Thinking for multi-turn agentic work.
Tests how many AI agents the ASUS ExpertCenter Pro ET900N G3 can run using its 748GB unified memory, 400Gb networking, and 1400 watt superchip configuration.
Tests unsloth/Qwen3.8-27B-GGUF performance, memory, agency, OpenAI Human Eval, Kanban, Sand Physics, Dungeon Crawler, Blender and Godot on a 16GB local setup using llama.cpp.
Evaluates Qwen 3.8 27B locally through code reviews of a nontrivial feature branch and analysis of technical documentation for gaps or outdated information.
Tests Qwen 3.8 27B, Nemotron 3.5 Lightning, and Muse Glimmer on an RTX 5090 using 16 hard math, coding, and reasoning problems via Ollama with Q4_K_M quantization, measuring accuracy, time, VRAM, and
Tests Qwen3.8-27B locally on RTX 4090 via Unsloth Dynamic 4-bit quant and Open WebUI against Claude Opus in coding, agentic tasks, vision and web dev.
Installs and tests Qwen3.8-27B Quant locally using llama.cpp, Ollama, and LM Studio.
Evaluates Qwen3.8-27B-MLX-Q9 performance using Inferencer App v2.3.2 on M3 Ultra 512 GiB across one million tokens.
Demonstrates setup of Qwen 3.8 27B bootstrapped by Qwen 3.6 27B on local infrastructure, where Qwen 3.8 27B programs Super Dario.
Tutorial demonstrating Minimax Music 3 installation and workflows in ComfyUI, covering pop, punk, jazz genres, song editing, loop stacking, and conversion to MIDI.
Tests Qwen3.8 27B across browser OS, C++ skate game, Subway FPS, 3D CAD, watch website, creative chat, multimodal coding, Chrono City timeline, Cinematic Steve’s PC repair, and Street Yeet game.
Demonstrates building an AI Dark Factory using Archon and a ColeAm00 skill to automate specs into validated software via five components: workflow-driven repos, automation queues, blue-green deploymen
Locally evaluates Qwen3.8-27B against Qwen3.6-27B on coding, agents, tools, reasoning, hallucinations, speed, vision, Splunk CTF, and Mario clone creation.
Qwen3.8-27B runs locally on MacBook Pro M5 Max 128GB, evaluating speed, reasoning, coding, and offline performance via Pi coding agent and Mario game construction tasks.
Installs and tests Qwen3.8-27B locally.
Covers WorldClaw, Grok Bot, Seedance 2.5, Claude labels, Suno limits, Spotify badges, Grok 4.6, Gemini 3.7 Flash, Meta Muse Glimmer, NVIDIA Nemotron 3.5 Lightning, DeepSeek-V4-Pro, MAI-Code-1.1-Flash,
Tests GLM-5.3 on coding, frontend, agentic tasks, Terminal Bench, DeepSWE, and AutomationBench, comparing against Kimi K3, DeepSeek-V4, Qwen3.8-Max, GPT-5.6 Sol, Opus 4.8, and Fable 5.
Tests local installation of MiniMax-Music3 for generating Bollywood, Cumbia and pop music using resources from huggingface.co/MiniMaxAI/MiniMax-Music3.
Meta Muse Glimmer, Qwen3.6 35B-A3B, Qwen3-Coder 30B, and GPT-OSS 20B compete in 10 frozen events on GMKtec EVO-X2 via Ollama on ROCm, judging speed and accuracy across tasks like coding, image generat
Demonstrates using GLM-OCR, Qwen 3.5 4B, and MedGemma on a ZimaCube 2 for OCR, summarization, private assistance, and translation.
Installs and tests North Micro Vision Instruct, an open-weight vision-language model with native-resolution image support.
Grok 4.6 is tested via browser OS, C++ Skate Game, 3D CAD Model Print, iPod Mini Frontend, Wedding Website, Subway FPS, and Street Yeet Game tasks.
Evaluates NVIDIA Nemotron 3.5 Lightning 30B A3B via Performance, Memory, Agency, OpenAI Human Eval, Kanban, Sand Physics, Dungeon Crawler, Blender and Godot tests on a 16GB local setup.
Qwen3.8 is presented as the most capable generation in the Qwen open-model family, featuring the Qwen3.8-2.4T-A95B variant.
Tests Grok 4.6 on coding, agentic workflows, visual generation, Three.js, and real-world tasks versus GPT-5.6 Sol, Claude Opus 5, Kimi K3, and Grok 4.5 using woaibench.ai.
Explains Qwen 3.8 2.4T parameters, Unsloth 1-bit builds requiring 450GB RAM, GGUF format, mixture of experts architecture, vendor benchmarks versus independent testing, and licensing distinctions.
A private benchmark suite evaluates Muse Glimmer, finding it does not measure up against Qwen.
Builds The Librarian 2 using Claude Code with Opus 5 and Codex with GPT-5.6 Sol, resulting in a 3D procedurally generated roguelite with 10,400 lines of code across 33 modules and zero asset files.
Tests DeepSeek V4 Pro across browser workflows, C++ game development, FPS generation, 3D CAD modeling, frontend design, and cinematic game creation.
Demonstrates minimalistic skills for Claude Code and Codex to manage PRDs, specs, ticket slicing, planning, validation, implementation, and code reviews within an enterprise development workflow.
Benchmark comparisons of Muse Glimmer against Qwen and Kimi K3 using Inferencer App v2.3.2 on M3 Ultra 512 GiB hardware.
Benchmarking DeepSeek V4 Flash 284B with DSpark on RTX PRO 6000 via llama.cpp measures 31 tok/s using multi-turn coding sessions and tests drafter placement in RAM versus VRAM.
Tests DeepSeek-V4-Pro-0813 via API and chat platforms, showing high performance in agent tests.
Latency, tokens and costs were tracked while building a 3D model of the 1903 Wright Flyer in a single HTML file using Three.js with orbit controls.
Meta Muse Glimmer implements a Solar Fortress clone using a 7-stage development plan, replicating the LLM Battle 5 challenge previously applied to three Qwen models.
Tests Nemotron 3.5 Lightning performance on browser workflows, C++ coding, 3D CAD modeling, frontend design, long-context recall, niche knowledge, and roleplay tasks.
Benchmark compares Nemotron 3.5 Lightning and Muse Glimmer 30B on an RTX 5090 using needle-in-haystack, math, logic, JSON, knowledge, and coding tests at 64,000 tokens, measuring speed, VRAM, and thin
Evaluates Muse Glimmer 30B versus Qwen 3.6 27B via woaibench.ai, covering benchmarks, agentic capabilities, tool use, coding, efficiency, DFlash speculative decoding, and local hardware requirements.
Locally installs and tests NVIDIA NeMo Switchyard with Ollama and other models to route agent workloads across specialized and frontier models.
Evaluates Muse Glimmer performance on an AMD Ryzen AI Max machine via Ollama and Open WebUI, comparing Meta’s metrics against independent benchmarks including admitted hallucination rates.
Tutorial covering ComfyUI integration for MiniMax H3 using Spectrum, Kijai TAE live preview, Realism LoRAs, Turbo variants, GGUF quantization, and workflows optimized for low VRAM environments.
Installs and tests NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4, a large language model trained by NVIDIA.
Locally tests Muse Glimmer 30B via Muse Code with SGLang and vLLM against Qwen3.6-27B and Gemma4-31B on tool use, agent workflows, vision, coding, reasoning, long context, and Estonia benchmark.
Compares Qwen 3.6 35B A3B, Qwen 3.6 27B dense, and Qwen 3.6 Fable Fusion by having each recreate the Solar Fortress arcade game using an Arcade Template.
Upstage Solar Pro 4 is tested on browser-based workflows, C++ game creation, 3D CAD modeling, FPS development, creative writing, writing assistance, and frontend design.