ViewTube

ViewTube
Sign inSign upSubscriptions
Filters

Upload date

Type

Duration

Sort by

Features

Reset

58 results

Tech-Practice
DeepSeek-V4-Flash-0731 (284B) run Locally on 4 RTX3090s

In this video, I build a 4x RTX 3090 machine from scratch and run DeepSeek-V4-Flash-0731 fully offline using llama.cpp — no API ...

10:08
DeepSeek-V4-Flash-0731 (284B) run Locally on 4 RTX3090s

668 views

5 hours ago

Cloud Codes
Run "DeepSeek V4 Flash 0731" Locally (No GPU Needed)

DeepSeek V4 Flash 0731 just dropped as a massive 284B parameter Mixture-of-Experts (MoE) model, natively trained in MXFP4, ...

15:29
Run "DeepSeek V4 Flash 0731" Locally (No GPU Needed)

23,413 views

18 hours ago

Better Stack
This component library is mind-blowing (Canvas UI)

Canvas UI is an open source library of 33 html-in-canvas and WebGL components that run GPU effects over live, interactive HTML ...

7:27
This component library is mind-blowing (Canvas UI)

4,831 views

4 hours ago

Cloud Codes
Run "Kimi K3" on a Laptop With 32 GB Ram (No GPU Needed)

Is it actually possible to run a 2.78-trillion parameter frontier AI model on a single consumer laptop with only 29 GB of RAM?

16:14
Run "Kimi K3" on a Laptop With 32 GB Ram (No GPU Needed)

9,516 views

14 hours ago

AI Search
New Deepseek, Seedance 2.5, Minimax H3, Gemini Robotics, AMD models: AI NEWS

HUGE AI NEWS: Deepseek V4 Flash, Seedance 2.5, Minimax H3, Kimi K3 & more #ai #ainews #aitools #aivideo #agi Thanks to ...

28:10
New Deepseek, Seedance 2.5, Minimax H3, Gemini Robotics, AMD models: AI NEWS

16,224 views

3 hours ago

WebKnower
The Truth Behind Linus Torvalds And NVIDIA

The Day Linus Torvalds Destroyed NVIDIA The real story behind Linus Torvalds, NVIDIA, and one of the most unforgettable ...

1:24
The Truth Behind Linus Torvalds And NVIDIA

137 views

17 hours ago

Better Stack
Local AI On Apple Silicon uses 7X Less RAM

Turbo Fieldfare runs a 26 billion parameter Gemma 4 model on a Mac in about 2GB of RAM, streaming most of the weights off the ...

6:56
Local AI On Apple Silicon uses 7X Less RAM

32,129 views

22 hours ago

dustmite
[OpenGL & C Game Engine Dev] Directional Maps and Chill

join the discord! https://discord.gg/ez6axU9JAv commands: !specs !keyboard !font !theme !discord We will be moving the lightmap ...

6:51:44
[OpenGL & C Game Engine Dev] Directional Maps and Chill

413 views

Streamed 7 hours ago

Jim Pavloff
My new Wolfenstein 3D Game Engine (Demo)

Those, who knows me well, also know about my passion in programming computer games. While I was already good at making ...

9:22
My new Wolfenstein 3D Game Engine (Demo)

96 views

5 hours ago

DHCAST
How to Turn Your Laptop/Tablet Into a Gaming PC With an eGPU (RTX 5070 Ti + Thunderbolt 4)

I installed a desktop graphics card (RTX 5070 Ti) in my Surface Pro 9 using an eGPU connected via Thunderbolt 4. In this video ...

8:07
How to Turn Your Laptop/Tablet Into a Gaming PC With an eGPU (RTX 5070 Ti + Thunderbolt 4)

10 views

8 hours ago

Cloud Codes
Python vs TypeScript: Which One for AI?

Is Python actually losing popularity, or are programming language rankings like TIOBE completely broken in the AI era?

10:05
Python vs TypeScript: Which One for AI?

1,694 views

11 hours ago

Arab Teach
Which Programming Language Should You Learn? (21 Languages Compared)

The grand finale is here! Wrap up our 21 Programming Languages Explained series with this ultimate completion video.

16:05
Which Programming Language Should You Learn? (21 Languages Compared)

10 views

19 hours ago

Darshil Parmar
Zomato AI Data Pipeline | End-To-End AI Data Engineering Project

Become a Job-Ready Data Engineer - https://datavidhya.com/ Build a complete AI Data Engineering project from scratch ...

4:31:06
Zomato AI Data Pipeline | End-To-End AI Data Engineering Project

4,309 views

17 hours ago

TechTrendsToday
Proton VPN's Stealth Protocol Lands on Linux, Evading Censorship

Daily Tech News Update! Proton VPN's anti-censorship Stealth protocol finally lands on Linux Proton VPN has launched ...

7:48
Proton VPN's Stealth Protocol Lands on Linux, Evading Censorship

25 views

10 hours ago

JustAIWorld
NEW Qwythos-27B-v1 is INSANE!

Empero AI — a small independent research lab — just released Qwythos-27B-v1, a FREE open-weight AI model that can ...

8:00
NEW Qwythos-27B-v1 is INSANE!

674 views

15 hours ago

KootJam
How To Talk Verity Offline? (Ollama + Verity Setup Update)

How To Talk Verity Offline? (Ollama Local LLM + Verity Minecraft JE Mod Up To 5.7.3 Setup and Unlimited Conversation) You can ...

5:08
How To Talk Verity Offline? (Ollama + Verity Setup Update)

743 views

22 hours ago

Tappy Coder
How ChatGPT Actually Works Behind the Scenes (AI Explained)

Ever wondered what happens behind the scenes when you ask ChatGPT a question? In this video, we break down the entire ...

1:50
How ChatGPT Actually Works Behind the Scenes (AI Explained)

3 views

22 hours ago

SimplyExplain
Kimi K3 on a MacBook: How 1.56 TB Runs on 64 GB (Deltafin)

The largest open-weights model ever released is 1.56 terabytes. It does not fit in your memory, and it will never fit. Somebody is ...

6:55
Kimi K3 on a MacBook: How 1.56 TB Runs on 64 GB (Deltafin)

26 views

18 hours ago

DigitalWeekly-Ai
This Week in AI: MiniMax H3 2K Video, DeepSeek V4‑Flash Update, Supabase Evals, LingBot‑Map

Roundup and technical synthesis of four developer- and model-focused releases. Short summary, context, and links to the primary ...

7:35
This Week in AI: MiniMax H3 2K Video, DeepSeek V4‑Flash Update, Supabase Evals, LingBot‑Map

4 views

17 hours ago

Uplatz
The 2026 AI Production Blueprint | Navigating Cost, Quality & Security at Scale | Uplatz

In this video by Uplatz, we explore the 2026 AI Production Blueprint, a practical framework for building, deploying and operating ...

6:07
The 2026 AI Production Blueprint | Navigating Cost, Quality & Security at Scale | Uplatz

1 view

9 hours ago