Upload date
All time
Last hour
Today
This week
This month
This year
Type
All
Video
Channel
Playlist
Movie
Duration
Short (< 4 minutes)
Medium (4-20 minutes)
Long (> 20 minutes)
Sort by
Relevance
Rating
View count
Features
HD
Subtitles/CC
Creative Commons
3D
Live
4K
360°
VR180
HDR
21,144 results
An NVIDIA engineer just made llama.cpp read long prompts up to 41% faster on NVIDIA GPUs, and it's a free update. The gain ...
10,249 views
19h ago
Get The Canadian Seniors' Money Playbook here: https://jakemorrison.gumroad.com/l/Playbook Every January your CPP and Old ...
56,225 views
5d ago
Get The Canadian Seniors' Money Playbook here: https://jakemorrison.gumroad.com/l/Playbook Every Thanksgiving, Gord raises ...
1,109 views
4h ago
llama.cpp just hit version 1.0.0. And one line in the release notes matters to anyone running a model bigger than their GPU: the ...
39,455 views
4d ago
Book a call with me here: https://calendly.com/ksthilaire-designedsecurities/30min Get Your FREE Retirement Spending Playbook ...
9,553 views
llama.cpp v1.0 released #ai #machinelearning #datascience.
900 views
Developer Bootcamp & Mentoring Program — Start or level up your career with my proven training and personal mentoring: ...
15,989 views
A surprisingly small machine is doing something that sounds impossible. But there's a lot more happening behind that 22 ...
61,823 views
6d ago
My System Design course: https://codinggopher.com/courses/system-design?utm_source=youtube&utm_campaign=new-video ...
7,117 views
1d ago
Interested in a custom retirement strategy? ➡️ https://willemswealthplanning.ca/start-here == Steve Willems, CFP®, FEA, BA ...
8,330 views
Forty-seven students, twelve seats per minibus, and C++ says you need three buses. Eleven students just vanished.
7 views
14h ago
llama.cpp vs Ollama in November 2026: llama.cpp's new MoE cache with the CPU share runs local LLM mixture of experts ...
12,396 views
Get The Canadian Seniors' Money Playbook here: https://jakemorrison.gumroad.com/l/Playbook A headline about an American ...
5,890 views
3d ago
Llama.cpp 1.0 update testing on a 12GB GPU. I show how two ignored settings increased my performance by 68 percent.
10,800 views
2d ago
CPP and OAS alone? Track your real TFSA room for free in my app. https://hudsonbayfinance.ca/go/yt Paid links: Wealthsimple ...
1,302 views
llama.cpp 1.0 is out, but Ollama and LM Studio don't run it yet. Here's what changes for AI on your laptop, and the 8-bit Gemma 4 ...
753 views
If you run Mixture-of-Experts (MoE) models on a graphics card with 8 GB, 11 GB, or 16 GB of VRAM, your model's unheld experts ...
6,106 views
7d ago
Ever wondered how AI models run locally without relying on cloud services? In this video, I'll break down how llama.cpp makes it ...
152 views
tandem.cpp is a new patch for llama.cpp, and on a 16GB RTX 5070 Ti with 64GB of RAM it takes DeepSeek V4.1 Flash from 7.4 to ...
8,950 views
Fil-Can Living: We provide information, education, and entertainment about retirement and personal finance.
1,347 views