ViewTube

In this video, I look at MiniCPM5 from OpenBMB. This 1B model is certainly punching above its weight for agentic use cases and is ...

MiniCPM5-2B is a tiny 2B-parameter local LLM that claims to beat Qwen3.5-4B on SWE-bench Verified, but the real story gets ...

How to train your own 10M parameter LLM | Get started with SerpApi using 250 free credits: ...

I Made ChatGPT-2 Run on a Potato (63MB AI Model!) - Extreme Quantization Experiment What happens when you compress a ...

The Qwen3 family of thinking large language models has just been released and the smallest model in the family is just 523MB!

You don't need a big model to do RAG well. LiquidAI's new 1.2B RAG model is so good in my quick RAG testing it was on par with ...

Tiny LLMs are making on-device agents much more practical. In this workshop, Cormac Brick walks through how LiteRT-LM ...

In this video, I take on the challenge of running a Large Language Model (LLM) on the ESP32 microcontroller. Using a model ...

Function Gemma ships at 270 million parameters and processes nearly 2000 tokens per second prefill on a Pixel 7. Out of the box ...

arxiv.org/pdf/2412.15304.

A developer got a 28.9-million-parameter language model running entirely offline on an $8 ESP32-S3 microcontroller, a chip with ...

Check out HubSpot's AI Decoded Guide: https://clickhubspot.com/c7a843 A tiny 27M parameter “recursive” model is suddenly ...

Ready to become a certified watsonx AI Assistant Engineer? Register now and use code IBMTechYT20 for 20% off of your exam ...

A one billion parameter model just refused to do math — and called a calculator instead. No GPU. No cloud. Just a CPU and a ...

In this video, we will go through the entire instruction tuning or Supervised Finetuning (SFT) phase. We will take raw unstructured ...

I paired a tiny AI box with the MacBook Neo—and it seriously changed what I thought was possible with local AI. Tiiny box: ...

See Tiiny Here: https://www.kickstarter.com/projects/tiinyai/tiiny-ai-pocket-lab?ref=c46bcy Timestamps: 00:00 - Intro 00:35 - First ...

Are 2026's small local LLMs better than last year's champion? I tested Qwen3.5 (2B/4B/9B), Granite 4.2 3B, Gemma 4 E2B and ...

How does an LLM actually learn? Where do the billions of parameters inside models like Mistral come from? In Part 6 of LLMs ...

mini-AGI is an open-source language model you can train from absolute zero on a single consumer GPU, and it's designed to ...