Which Qwen3 Model - Search Videos

Only 22B is active in a 671B model?😐 Why are top models suddenly 5–10× more efficient without losing smarts? Anyscale engineers drop an 11-minute masterclass, breaking down the real infra behind it. The MoE magic why expert parallelism beats tensor-parallel every time. 😑 This clip is gold for anyone building real AI infra. 🙌 Only 22B is active in a 671B model. 🥹 Mixture of Experts (MoE) magic: 671B total params… but only 3% 22B activate per token. - Expert parallelism crushes KV-cache nightm

Only 22B is active in a 671B model?😐 Why are top models suddenly 5–1…

157 views1 month ago

FacebookMd Ismail Sojal

Falcon H1R 7B: UAE s Reasoning Model with Mamba Beats 32B Models | Fahd Mirza

Falcon H1R 7B: UAE s Reasoning Model with Mamba Beats 32B Mod…

9.5K views2 months ago

⚡️ Qwen3-Coder-Next: Alibaba’s open model built for coding agents, not just code Alibaba just dropped Qwen3-Coder-Next, an open-weight language model optimized for agentic coding and local dev workflows. What’s new • Agent-first training at scale: 800K verifiable coding tasks paired with executable environments • Efficiency over brute force: 80B total params, but only 3B active, delivering strong SWE-Bench Pro results • Plug-and-play with real tools: Works with OpenClaw, Qwen Code, Claude Code,

⚡️ Qwen3-Coder-Next: Alibaba’s open model built for coding agent…

1 views1 month ago

FacebookAndy Frenzy

How to use or disable Model Thinking in Ollama (Python Tutorial)

How to use or disable Model Thinking in Ollama (Python Tutorial)

Alibaba Shares Surge On Expanded AI Push, New Qwen3-Max Model, And Global Data Center Plans

Alibaba Shares Surge On Expanded AI Push, New Qwen3-Max Model, …

Alibaba Luncurkan Qwen3, Model AI Open-Source Mampu Berpikir Panjang dan Lebih Manusiawi

Alibaba Luncurkan Qwen3, Model AI Open-Source Mampu Berpikir Pan…

MashableIrfan Fikri

Alibaba’s Qwen3 topples DeepSeek’s R1 as world’s highest-ranked open-source AI model

Alibaba’s Qwen3 topples DeepSeek’s R1 as world’s highest …

South China Morning PostBen Jiang

Running and Testing an AI model on Old Hardware

2 views6 months ago

YouTubeAnderson Leonardo

Build a Killer Sudoku AI Solver Fast

64 views3 weeks ago

YouTubeojamboshop

DOTNET9 SEMATIC KERNEL WITH FUNCTION CALLING QWEN3 MOD…

5 views2 months ago

YouTubeChatri Ngambenchawong (Pingkung Debugging)

Mark Johns — Origins of Doomlaser + Importance of Local AI

33 views1 month ago

YouTubeDoomlaser

Using Supervised Fine-Tuning to Teach Qwen3 the Secrets No Othe…

3 views3 months ago

YouTubeDeepExtension

Build a 3D Megaminx with Local AI

YouTubeojamboshop

PyTorch Autograd Explained - In-depth Tutorial

135.2K viewsNov 3, 2018

YouTubeElliot Waite

Qwen3发布刷屏海外，国产开源模型封神时刻

25.3K views10 months ago

bilibili赛文乔伊

Qwen3测评报告：这个模型很天马行空！

2.5K views10 months ago

bilibiliAI产品狙击手

Qwen3 + MCP

6K views10 months ago

YouTubeChris Hay

Qwen3 - Paper Walkthrough

1.5K views8 months ago

YouTubeDataMListic

DeepSeek-R1 Crash Course

442.9K viewsJan 28, 2025

YouTubefreeCodeCamp.org

Qwen3 Technical Report

240 views10 months ago

Ollama Course – Build AI Apps Locally

586.8K viewsNov 26, 2024

YouTubefreeCodeCamp.org

I Made The Smallest (And Dumbest) LLM

467.4K views6 months ago

YouTubeCodeically

Qwen3-VL is here!

776.6K views5 months ago

Qwen3 Omni | Multimodality, Grounding, LLM

7.8K views5 months ago

YouTubeCaleb Writes Code

Neo4j's LLM Knowledge Graph Builder - DEMO

43K viewsJun 19, 2024

Qwen3 Multimodal Embeddings: Finally, RAG That Sees

21.1K views1 month ago

YouTubeSam Witteveen

The AI News We Can't Stop Talking About

40 views5 months ago

YouTubeThe Daily AI Show

Qwen3-TTS: The ElevenLabs Killer?

16.1K views1 month ago

YouTubePrompt Engineering

Qwen 3 in 8 Minutes

26.6K views10 months ago

YouTubeDevelopers Digest

Your Laptop Just Became an AI Agent

28 views4 months ago

YouTubeAI Tools Quest

See more videos