Video
Fahd Mirza
2026-09-11
Run 35B Model on Phone Under 3GB Memory with Edge0
Introduces edge0, an open-source streaming MoE inference framework.
Videos
Videos about AI and LLM
Find videos about LLM models, hardware, runtimes, benchmarks and practical AI workflows.
810 videos found
Showing 51-100
Video
AI with Eric
2026-09-11
DeepSeek-v4.1-Flash Kept Hallucinating - Here's What Helped
Demonstrates DeepSeek V4.1 Flash hallucinations in agentic cybersecurity and coding, explains sparse attention's role in missed context, and shows methods to reduce errors using the AA Omniscience Hal
Video
KGP Talkie
2026-09-11
DeepSeek V4.1 Flash Architecture Explained: DSA and CSA2 Sparse Attention
Explains DeepSeek V4.1 Flash using DeepSeek Sparse Attention and Compressed Sparse Attention 2 to limit reads to 640 entries per layer with an 890-byte KV cache per token via the lightning indexer.
Video
Matt Wolfe
2026-09-11
AI News: The AI World is REALLY Scared Right Now
Covers ChatGPT Images 2.5, Meta Muse, DeepSeek-V4.1-Flash, Anthropic warnings, OpenAI updates, Apple announcements, MAI-Image-2.6, Gemini App, Suno, Lyria 3.5, and DaVinci Resolve 21.1.
Video
Execute Automation
2026-09-11
I Built an Auto Router for Local LLMs with LiteLLM + Pi Coding Agent
Demonstrates LiteLLM Auto Router with Pi Coding Agent, Ollama, and oMLX on Apple Silicon, comparing heuristic versus LLM classifiers for Qwen3.5 4B, Gemma 4, and Qwen3.8 27B.
Video
Luke's Dev Lab
2026-09-11
Nail Qwen 35B A3B tested - 16GB Local LLM setup
Tests Nail Qwen3.6-35B-A3B-GGUF-MTP via Performance, Memory, Reasoning, OpenAI HumanEval, Kanban, Sand Physics, Dungeon Crawler, Blender and Godot on a 16GB local setup.
Video
Donato Capitella
2026-09-11
Qwen3.8-Flash-Next on AMD Strix Halo: Halogen, N-grams and Benchmarks
Compares Halogen Flash Server, EngramHalo and ROCm/Vulkan llama.cpp for Qwen3.8-Flash-Next on AMD Strix Halo via Terminal Bench Mini agentic tasks and speed benchmarks.
Video
Fahd Mirza
2026-09-11
OUI-1: Builds UI Screens Instantly Locally
Locally installs OUI-1, identified as the first diffusion model built for generative UI.
Video
xCreate
2026-09-11
I Ran DeepSeek V4.1 Locally for 24 Hours... Local AGI is HERE!? 🤯
Runs DeepSeek-V4.1-MLX-Q4i via Inferencer v2.2.8 on Mac Studio M3 Ultra 512, testing math, coding, logic, office apps, canvas animations, 3D simulations, games, and image generation.
Video
Fahd Mirza
2026-09-10
Ling-3.0-flash-VL: Free Vision Model Standing on Kimi's Shoulders
Tests Ling-3.0-flash-VL, described as a native multimodal model.
Video
KGP Talkie
2026-09-10
LangChain Tutorial for Beginners: Vector Database and RAG Ingestion
Demonstrates RAG ingestion using LangChain, RecursiveCharacterTextSplitter, embeddings, and Qdrant via Docker, covering chunk sizing, cosine similarity, and metadata filtering.
Video
Bijan Bowen
2026-09-10
DeepSeek V4.1 Flash Is INSANE – Is THIS the Best Open Model Yet?
Evaluates DeepSeek V4.1 Flash via browser OS tests, C++ skate and rally games, robot arm control, Subway FPS, Blender & Godot wrestling, 3D CAD models, and watch website design.
Video
No place like localhost
2026-09-10
Cloning AI voices with emotion
Demonstrates exposing TTS engine tuning parameters in TalkWithMe using Chatterbox, IndexTTS, and tts-serve to imbue emotion into cloned voices.
Video
Fahd Mirza
2026-09-10
Nex-N2.5 Mini: Multilingual, Multimodal, and Fully Agentic (Hands-On)
Installs and tests Nex-N2.5 mini, an agentic model, using RunPod for GPU compute.
Video
AI Search
2026-09-10
New BEST AI image generator is here
Reviews GPT Image 2.5 against GPT Images 2 and Nano Banana 2, demonstrating sketch features, multi-turn editing, transparency, typography, spatial understanding, reference consistency and specs.
Video
Cole Medin
2026-09-10
No One Talks Enough About Security for AI Coding. Here's How I Do It in My Workflows
Demonstrates using Archon and SonarQube Cloud in a workflow where Sonar acts as a non-skippable security gate to catch vulnerabilities in AI-generated code before shipping.
Video
Fahd Mirza
2026-09-09
DeepSeek V4.1 Flash: The New Speed King That Also Thinks Straight
Tests DeepSeek V4.1 Flash by building a 3D Viewer, catching an ATC bug, and solving physics problems from scratch.
Video
Unbiased Bob
2026-09-09
Qwen Carbon Copy "Dirk" Decisively Dismantled in Brutal Benchmark Brawl
Dirk, identified as Qwen 3.8 27B with modified templates, is benchmarked against Qwen 3.8 on Bob-bench to evaluate its actual performance capabilities.
Video
Execute Automation
2026-09-09
GLM-5.3-Flash 320B on M5 Max: Can It Beat Qwen3.8-Flash-Next?
Tests GLM-5.3-Flash 320B on M5 Max against Qwen3.8-Flash-Next via MTPLX, .NET migration, and SVG generation, analyzing quantization effects on memory, accuracy, and KLD.
Video
Luke's Dev Lab
2026-09-09
Portable Qwen 3.8 27B on a ZimaBoard 2
Runs Gemma4 E4B and Qwen 3.8 27B on ZimaBoard 2 using llamacpp, comparing performance with an added RTX 2000 GPU through Kanban, Sand Physics, and Dungeon Crawler demos.
Video
Bijan Bowen
2026-09-09
Gemini 3.8 Flash Is HERE – Testing Google’s BEST Model Yet!
Tests Gemini 3.8 Flash performance in browser workflows, C++ game development, frontend design, FPS generation, robot arm control, and Blender and Godot workflows.
Video
WorldofAI
2026-09-09
DeepSeek V4.1 Flash Is INSANELY GOOD! Fast, Cheap, Powerful! (Fully Tested)
Tests DeepSeek V4.1 Flash on coding, 3D simulations, Three.js, games, agentic tasks and vision, noting speed of 300–400+ tokens per second and pricing against frontier models.
Video
Jose Romero
2026-09-09
GLM-5.3-Flash: which quant works on a Strix Halo
Tests Unsloth quants of GLM-5.3-Flash on GMKtec EVO-X2 using llama.cpp across four one-shot tests at low, high, and max reasoning settings.
Video
Fahd Mirza
2026-09-09
Qwen Gifts ZG: Local-First Semantic grep for You and Your AI Agent
Locally installs and tests zg (zvec-grep) powered by zvec, which unifies ripgrep, BM25, and vector search.
Video
xCreate
2026-09-09
I Ran GLM 5.3 at MAX Locally for 200+ Hours... Forget GPT-6 & Fable 🤯
Evaluates GLM 5.3 MLX Q4i on Mac Studio M3 Ultra across Low, High, Max and MinMax thinking modes using coding tasks and complex simulations.
Video
Unbiased Bob
2026-09-08
Bob-Bench Tier List - 31 Local Coding LLMs Ranked
Ranks local coding LLMs into tiers based on quality, size relevance, and efficiency, covering Qwen variants, Dirk, OLMo, and others across different GPU constraints and quantizations.
Video
Lukasz Gawenda
2026-09-08
Qwen3.8 Flash: Over 7x Faster First Token | llama.cpp vs SGLang vs FreeToken. Benchmarked!
Compares Qwen3.8-Flash-Next inference via llama.cpp, SGLang, and FreeToken on RTX PRO 6000 Blackwell using AIPerf, measuring first-token latency, decode speed, accuracy on GSM8K/MATH-500, and startup
Video
KGP Talkie
2026-09-08
LangChain Tutorial for Beginners: Build an AI Agent with Memory
Demonstrates building a LangChain agent using create_agent with multiply and web search tools, comparing invoke versus stream modes, measuring token usage, applying ModelCallLimitMiddleware, and enabl
Video
No place like localhost
2026-09-08
Harness review: Oh My Pi
Compares Oh My Pi with Pi and OpenCode through initial setup, configuration tweaks, built-in tools, custom system prompts, compaction methods, sub-agents, and design philosophy analysis.
Video
Fahd Mirza
2026-09-08
MiniCPM5-2B GGUF: Runs Great, Until It Doesn't
Tests MiniCPM5-2B in GGUF format, identifying it as the second model in the MiniCPM5 series hosted on Hugging Face under openbmb.
Video
Fahd Mirza
2026-09-07
MiniCPM5 2B: SOTA or Scam? Let's Test Locally
Tests MiniCPM5-2B locally.
Video
Fahd Mirza
2026-09-07
Qwen3.8-27B GSQ+RCO: 27B Params, 11.8GB, Zero Accuracy Lost Locally
Locally installs and tests ISTA-DASLab Qwen3.8-27B-GSQ-RCO-GGUF models using GSQ and RCO quantization methods.
Video
Execute Automation
2026-09-07
M5 Max 128GB After 5 Months: How Far Can You Push Local AI?
Runs local LLMs like Qwen3.8, GLM-5.3 Flash, Gemma, Muse/Glimmer and coding agents Pi, Codex via LM Studio, oMLX, MTPLX, Ollama, llama.cpp on M5 Max.
Video
Bijan Bowen
2026-09-07
GPT-6 Astra vs Claude Fable 5.1 – The REAL Comparison Test!
Compares GPT-6 Astra and Claude Fable 5.1 using Hot Wheels physics simulation, Vision Pro FPS task, robot arm control, software efficiency, and Steve PC game build tests.
Video
Luke's Dev Lab
2026-09-07
Tiel Coder 35B A3B tested - 16GB Local LLM setup
Tests Tiel Coder 35B A3B performance, memory, reasoning, OpenAI Human Eval, Kanban, Sand Physics, Dungeon Crawler, Blender and Godot on a 16GB local setup.
Video
WorldofAI
2026-09-07
Ponytail Makes Claude Code Write 94% Less Code!
Tests Ponytail, a Claude Code plugin, on real coding tasks to evaluate its ability to reduce generated code volume by up to 94% while maintaining functionality and quality.
Video
Fahd Mirza
2026-09-07
GPT-6 Astra: AGI Arrived Again - Checked From Sydney
Checks whether GPT-6 Astra represents the arrival of AGI.
Video
AI Search
2026-09-07
GPT 6 Astra is a freak
Reviews GPT 6 Astra capabilities across physics, ray tracing, Unreal video games, drawing, sprite animation, music composition, VR real estate, product commercials, math explainers, image identificati
Video
AI with Eric
2026-09-07
Qwen3.8-Flash-Next + DeepSeek Harness: My New Daily Driver
Demonstrates Qwen3.8-Flash-Next on 4x RTX 3090s using DeepSeek Harness with MiniMax H3 for autonomous music video creation, comparing throughput against Qwen3.8-27B.
Video
Codacus
2026-09-06
Is Frontier Class Local AI Finally Practical?
Benchmarks unsloth/Qwen3.8-Flash-Next-GGUF on RTX 3060 using llama.cpp and thecodacus/spec-wins coding lab with contradictory specs and decoys.
Video
Fahd Mirza
2026-09-06
How to Scan AI Agent Skills for Hidden Malware: NVIDIA SkillSpector
SkillSpector detects vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in AI agent skills.
Video
KGP Talkie
2026-09-06
Qwen 3.8 27B on MacBook Pro M5 Max vs RTX 5090: 31 vs 134 Tokens/s
Benchmark Qwen 3.8 27B Q4_K_M via llama.cpp on MacBook Pro M5 Max versus RTX 5090, analyzing memory usage, GGUF headers, KV cache behavior, and MTP drafting performance at 8K context.
Video
Fahd Mirza
2026-09-06
OmegaClaw: An AI Agent Built on Symbolic Logic, Not Just an LLM
Locally installs and tests OmegaClaw, a neural-symbolic agent framework based on the Hyperon AGI stack.
Video
WorldofAI
2026-09-06
GPT-6 Astra IS INSANE! Best Usecases & Tricks...
Demonstrates GPT-6 Astra use cases including one-shotting games, controlling computers via OpenAI's upgraded harness, building 3D environments in Blender and Unity, and operating real-world robots.
Video
AI Search
2026-09-06
GPT 6 Astra, Claude Fable 5.1, Gemini 3.8, realtime Minimax, new world models: AI NEWS
Covers GPT 6 Astra, Claude Fable 5.1, Gemini 3.8 Flash, Muse Spark 1.3, H3 World, SolarWM, TimesFM, Lucida, VideoDeltaNet, LLaDA image, Deepseek v4 flash vision, Qwen 3.8 0902, WeatherNext 3, Fly brai
Video
Fahd Mirza
2026-09-06
Spark X2.5 4B: What a 4B Model Can and Can't Do Locally
Locally installs and tests Spark-X2.5-4B to evaluate its capabilities for making AI practical, efficient, and accessible.
Video
KGP Talkie
2026-09-05
LangChain Tutorial for Beginners: Tools and Tool Calling Explained
Demonstrates converting Python functions to LangChain tools using the @tool decorator, binding them via bind_tools, executing calls through .invoke(), and returning results as ToolMessage for USD to I
Video
Fahd Mirza
2026-09-05
Extropic Z1T: AI Models 100x More Energy Efficient Than GPUs?
Introduces Extropic Z1T, a family of transformer-like AI models designed for the Z1 chip rather than GPUs.
Video
xCreate
2026-09-05
I Ran Hy4 770B Locally for 48 Hours... Local AI is the Frontier! 🤯
Tests Hy4 Preview against GLM 5.3 using Inferencer App Q4-INF quantization on Mac Studio M3 Ultra 512 GiB via thinking mode performance, UI testing, censorship checks, complex code modification, game
Video
Jose Romero
2026-09-05
GLM-5.3-Flash on 128 GB: it runs. Should you?
Runs GLM-5.3-Flash 1-bit via Unsloth and llama.cpp on GMKtec EVO-X2, testing Blockfall, Eruption, Blind Artist, and The Ledger with 9.2–9.6 tok/s performance.