Open in app
Sign inGet started
NVIDIA cuGraph: 500x faster alternate for NetworkX for Graphs

NVIDIA cuGraph: 500x faster alternate for NetworkX for Graphs

cuGraph vs NetworkX for Graph Analytics codes explained
Go to the profile of Mehul Gupta
Mehul Gupta
NVIDIA cuGraph: Accelerate Graph Analytics with GPUs

NVIDIA cuGraph: Accelerate Graph Analytics with GPUs

RAPIDS cuGraph beginner’s tutorial
Go to the profile of Mehul Gupta
Mehul Gupta
OmniParser: Microsoft’s Breakthrough in AI-Powered UI Interaction

OmniParser: Microsoft’s Breakthrough in AI-Powered UI Interaction

Exploring OmniParser’s Potential to Automate User Interface Interactions for AI-Powered Efficiency
Go to the profile of Malyaj Mishra
Malyaj Mishra
OpenAI SearchGPT: ChatGPT with Internet and browsing tools

OpenAI SearchGPT: ChatGPT with Internet and browsing tools

A Better Alternative for Perplexity and Google Search
Go to the profile of Mehul Gupta
Mehul Gupta
What is an AI Agent?

What is an AI Agent?

AI Agent Basics in Generative AI
Go to the profile of Mehul Gupta
Mehul Gupta
Claude 3.5 : Click Buttons, Move Cursor, and Fill Forms with Computer Use

Claude 3.5 : Click Buttons, Move Cursor, and Fill Forms with Computer Use

Anthropic’s Claude3.5 Sonnet “Computer use” can perform computer tasks autonomously
Go to the profile of Mehul Gupta
Mehul Gupta
Run Flux.1 Dev on Google Colab, 8 GB GPU for free

Run Flux.1 Dev on Google Colab, 8 GB GPU for free

Flux.1 Dev text to image model quantization codes
Go to the profile of Mehul Gupta
Mehul Gupta
How to run OpenAI Swarm with Local LLMs using Ollama

How to run OpenAI Swarm with Local LLMs using Ollama

Codes explained with example for the Multi-AI Agent system
Go to the profile of Mehul Gupta
Mehul Gupta
BitNet.cpp vs Llama.cpp : Run LLMs on CPU

BitNet.cpp vs Llama.cpp : Run LLMs on CPU

Which framework to choose to run Large LLMs on CPU ?
Go to the profile of Mehul Gupta
Mehul Gupta
Microsoft BitNet.cpp : Framework for 1-bit LLMs

Microsoft BitNet.cpp : Framework for 1-bit LLMs

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Go to the profile of Mehul Gupta
Mehul Gupta
NVIDIA Nemotron-70B: New LLM beats GPT-4o and Claude 3.5

NVIDIA Nemotron-70B: New LLM beats GPT-4o and Claude 3.5

The best LLM leading the Generative AI race
Go to the profile of Mehul Gupta
Mehul Gupta
200 Blogs, 1 Bestseller, Countless Lessons

200 Blogs, 1 Bestseller, Countless Lessons

Published my 200th Data Science Blog today
Go to the profile of Mehul Gupta
Mehul Gupta
About Data Science in your pocketLatest StoriesArchiveAbout MediumTermsPrivacyTeams