Laxmi Kant | KGP Talkie - Invidious

Laxmi Kant | KGP Talkie

I left a $100K/year job to teach AI the way it is actually built.

I’m Laxmi Kant Tiwari, an IIT Kharagpur alumnus, startup founder, and the creator of KGP Talkie. After more than a decade of building AI systems across industry and academia, I chose to teach full time and help developers bridge the gap between following tutorials and shipping real products.

Here, you will learn to build production-ready AI agents, RAG systems, LLM applications, and machine learning products through practical, code-first projects. The lessons go beyond demos to cover architecture, deployment, evaluation, cost, scalability, and the challenges that emerge in production.

Everything I teach is grounded in real engineering experience, including building a startup and taking it to a successful exit.
Join more than 200,000 learners and learn how to turn AI concepts into reliable products that people can actually use.

View channel on YouTube

Switch Invidious Instance

Videos

newest

oldest

popular

8:54

Nemotron 3.5 Lightning 33B vs Claude Haiku 5.5: 5 Real Coding Tests, RTX 5090 vs the Cloud

Laxmi Kant | KGP Talkie

Shared 1 day ago

636 views

8:17

Claude Opus 5.5 vs GPT-6.1 Sol: 5 Real Coding Tests, Is the Expensive One Better?

Laxmi Kant | KGP Talkie

Shared 2 days ago

448 views

9:59

Agent Harness Explained: Claude Code, Codex, DeepSeek Harness, Hermes

Laxmi Kant | KGP Talkie

Shared 3 days ago

1.2K views

8:44

Ornith 1.5 35B-A3B vs Nemotron 3.5 Lightning 33B: 5 Real Coding Tests on My RTX 5090

Laxmi Kant | KGP Talkie

Shared 3 days ago

760 views

8:23

Gemma 4 31B vs Gemini 4 Argon: 5 Real Coding Tests, RTX 5090 vs the Cloud

Laxmi Kant | KGP Talkie

Shared 4 days ago

2K views

8:05

Qwen 3.8 27B vs Muse Glimmer 30B: 5 Real Coding Tests on an RTX 5090

Laxmi Kant | KGP Talkie

Shared 5 days ago

1.9K views

5:22

Qwen 3.8 27B vs Gemini 3.8 Flash: RTX 5090 vs the Cloud, 4 Real Coding Tests

Laxmi Kant | KGP Talkie

Shared 6 days ago

1.9K views

5:17

Qwen 3.8 27B vs GPT-6 Luna: RTX 5090 vs the Cloud, 4 Real Coding Tests

Laxmi Kant | KGP Talkie

Shared 1 week ago

2.1K views

5:16

Qwen 3.8 27B vs GPT-6.1 Sol: RTX 5090 vs the Cloud, 4 Real Coding Tests

Laxmi Kant | KGP Talkie

Shared 1 week ago

4.1K views

5:17

Qwen 3.8 27B vs GPT-6 Astra: RTX 5090 vs the Cloud, 4 Real Coding Tests

Laxmi Kant | KGP Talkie

Shared 1 week ago

6K views

4:24

Qwen 3.8 27B vs Claude Sonnet 5.5: RTX 5090 vs the Cloud, 4 Real Coding Tests

Laxmi Kant | KGP Talkie

Shared 1 week ago

2K views

9:32

Claude Code with OpenRouter: Free Models, No GPU (Windows Setup)

Laxmi Kant | KGP Talkie

Shared 1 week ago

1.6K views

8:48

Fine-Tune an LLM on MacBook with MLX LoRA | Bank Statement to Budget

Laxmi Kant | KGP Talkie

Shared 1 week ago

401 views

4:23

Qwen 3.8 27B vs Gemma 4 31B on RTX 5090: 4 Real Coding Tests

Laxmi Kant | KGP Talkie

Shared 1 week ago

8K views

8:37

Fine-Tune LLM for Search Relevance on MacBook - OLMo 2 + Hugging Face

Laxmi Kant | KGP Talkie

Shared 1 week ago

332 views

9:12

How to Use OpenAI Codex App on Windows (Free with ChatGPT, Step by Step)

Laxmi Kant | KGP Talkie

Shared 1 week ago

1.2K views

4:40

Qwen 3.8 27B vs Claude Opus 5.5 on RTX 5090: 4 Real Coding Tests

Laxmi Kant | KGP Talkie

Shared 1 week ago

3.4K views

9:05

Google Antigravity Tutorial for Beginners: Design and Build a Web App Free

Laxmi Kant | KGP Talkie

Shared 1 week ago

1.8K views

9:26

n8n + Ollama: Build Local AI Agent with Qwen 3.8 27B (Free, Private)

Laxmi Kant | KGP Talkie

Shared 1 week ago

1.2K views

9:41

Kilo Code Setup in VS Code: Free Models

Laxmi Kant | KGP Talkie

Shared 1 week ago

1K views

10:15

Prompt Injection Firewall: Fine-Tune Falcon-H1 90M on MacBook with MLX

Laxmi Kant | KGP Talkie

Shared 2 weeks ago

412 views

4:34

NVIDIA Nemotron Parse vs LightOnOCR vs Docling: Invoice OCR Test

Laxmi Kant | KGP Talkie

Shared 2 weeks ago

426 views

11:48

OpenRouter Free AI Coding Models: Free AI API Key Setup (curl + Python, No Card)

Laxmi Kant | KGP Talkie

Shared 2 weeks ago

664 views

8:19

Qwen 3.8 27B on a MacBook vs Claude Opus: 4 Real Tests

Laxmi Kant | KGP Talkie

Shared 2 weeks ago

5.5K views

10:45

Fine-Tune MiniCPM5 on MacBook: SFT + DPO for a Brand-Voice Support Chatbot

Laxmi Kant | KGP Talkie

Shared 2 weeks ago

358 views

10:28

AnythingLLM: Chat with Your PDFs Offline with Ollama (Free, No Account)

Laxmi Kant | KGP Talkie

Shared 2 weeks ago

570 views

8:55

AI Agent Platforms Explained: Which One to Use? Copilot, Agentforce, Foundry, AgentCore

Laxmi Kant | KGP Talkie

Shared 2 weeks ago

496 views

8:53

Fine-Tune Gemma 3 270M on MacBook with Unsloth Studio (No Code)

Laxmi Kant | KGP Talkie

Shared 2 weeks ago

847 views

12:39

Codex CLI Setup on Windows: Sign In with ChatGPT

Laxmi Kant | KGP Talkie

Shared 2 weeks ago

739 views

13:09

llama.cpp Install on Windows: Run GGUF Models Fast

Laxmi Kant | KGP Talkie

Shared 3 weeks ago

2K views

12:27

Build Jev Like Model: Fine-Tune System 1 Decision Model

Laxmi Kant | KGP Talkie

Shared 3 weeks ago

628 views

10:49

OpenCode Setup: Free Claude Code Alternative with Free Models

Laxmi Kant | KGP Talkie

Shared 3 weeks ago

2.6K views

11:16

Fine-Tune IBM Granite 4.0 on MacBook with Hugging Face | Invoice PDF to JSON

Laxmi Kant | KGP Talkie

Shared 3 weeks ago

523 views

12:05

Open WebUI Install: Your Own ChatGPT with Ollama

Laxmi Kant | KGP Talkie

Shared 3 weeks ago

948 views

12:18

Fine-Tune Qwen 3.5 on MacBook with MLX | Fine-Tune LLM for Text to MySQL

Laxmi Kant | KGP Talkie

Shared 3 weeks ago

684 views

11:28

LM Studio Tutorial: Download Models and Start a Local Server

Laxmi Kant | KGP Talkie

Shared 3 weeks ago

1.3K views

12:46

Claude Code with Ollama: Free Local Setup on Windows (No Subscription, No API Key)

Laxmi Kant | KGP Talkie

Shared 3 weeks ago

2.4K views

12:07

DeepSeek Harness Desktop App: Free Setup on Windows (Ollama, No API Key)

Laxmi Kant | KGP Talkie

Shared 3 weeks ago

4.1K views

8:24

Ollama Setup on Windows: Install and Run Qwen 3.8 Locally (No GPU Needed)

Laxmi Kant | KGP Talkie

Shared 3 weeks ago

3.5K views

21:10

Context Language Models (CLM) Explained: LLMs That Manage Their Own Context

Laxmi Kant | KGP Talkie

Shared 1 month ago

1.3K views

28:01

MiMo 2.6 Pro and Flash Architecture Explained (Xiaomi MiMo V2.6)

Laxmi Kant | KGP Talkie

Shared 1 month ago

1K views

6:03

How GPUs Work for LLMs, and Why Memory Limits LLM Speed

Laxmi Kant | KGP Talkie

Shared 1 month ago

755 views

15:09

What is Jev and Laya Explained: Laya vs Qwen 3.5 Tested on MacBook M5 Max

Laxmi Kant | KGP Talkie

Shared 1 month ago

1.6K views

12:27

I Ran Inclusion's AI Ming Image 0.1 Design Locally

Laxmi Kant | KGP Talkie

Shared 1 month ago

1.3K views

20:53

Qwen Image 2.1 Low VRAM Test: 4-bit Runs Under 16 GB of RAM

Laxmi Kant | KGP Talkie

Shared 1 month ago

3.5K views

32:08

Do You Know How GLM 5 3 and GLM 5 3 Flash Works? DSA, KDA and KV Cache Explained

Laxmi Kant | KGP Talkie

Shared 1 month ago

576 views

48:16

LangChain Tutorial for Beginners: Build a RAG System with Langchain and RAGWire

Laxmi Kant | KGP Talkie

Shared 1 month ago

1.3K views

50:01

DeepSeek V4.1 Flash Architecture Explained: DSA and CSA2 Sparse Attention

Laxmi Kant | KGP Talkie

Shared 1 month ago

1.6K views

55:40

LangChain Tutorial for Beginners: Vector Database and RAG Ingestion

Laxmi Kant | KGP Talkie

Shared 1 month ago

911 views

52:52

LangChain Tutorial for Beginners: Build an AI Agent with Memory

Laxmi Kant | KGP Talkie

Shared 2 months ago

1.2K views

12:59

Qwen 3.8 27B on MacBook Pro M5 Max vs RTX 5090: 31 vs 134 Tokens/s

Laxmi Kant | KGP Talkie

Shared 2 months ago

8.4K views

52:56

LangChain Tutorial for Beginners: Tools and Tool Calling Explained

Laxmi Kant | KGP Talkie

Shared 2 months ago

1.3K views

1:04:01

LangChain Tutorial for Beginners: Short Term and Long Term Memory

Laxmi Kant | KGP Talkie

Shared 2 months ago

1.1K views

22:21

DeepSeek Harness (DSH) Setup with Qwen 3.8 27B Locally on Ollama - Full Tutorial

Laxmi Kant | KGP Talkie

Shared 2 months ago

16K views

35:08

LangChain Tutorial for Beginners: Structured Output with Pydantic

Laxmi Kant | KGP Talkie

Shared 2 months ago

866 views

35:17

I Ran DeepSeek V4 Flash vs Qwen 3.8 Flash Next Locally on CPU

Laxmi Kant | KGP Talkie

Shared 2 months ago

2.5K views

18:25

IBM Granite 4.2 vs Qwen 3.8 27B vs Gemma 4 - Local LLM Benchmark

Laxmi Kant | KGP Talkie

Shared 2 months ago

5.3K views

48:20

LangChain Tutorial for Beginners: LCEL Chains and Pipe Operator

Laxmi Kant | KGP Talkie

Shared 2 months ago

708 views

35:05

Ornith 1.5 35B vs Qwen 3.8 27B vs Gemma 4 - Local LLM Benchmark

Laxmi Kant | KGP Talkie

Shared 2 months ago

7.9K views

32:06

I Ran Qwen 3.8 Flash Next (Qwen 4) on CPU Only

Laxmi Kant | KGP Talkie

Shared 2 months ago

22K views