Nikhil Bhintade

I am one of those GPU Poor People, instead of getting RTX 5090 when it was cheaper I decided I just wanted to get RTX 5060Ti, who needs RTX 5090? They have their melting connector issues, high power consumption, etc. Turns out the answer was me, I NEED 5090 for running LLM models locally but I didn’t know that then. The result of my bad decision has been, I am stuck on running 7–14B parameter models (mostly quantized models) on my GPU. But recently that changed, now I can run the 125B model on my PC whil...

In this article, we are going to run the indexer that we created previously and explore the GraphQL API with Hasura Dashboard. Let’s me say this first, I know I said I am going to publish daily but I got caught up with some other things so I wasn’t able to publish articles. Now, I have next few days free so I am going to crank out multiple articles in that time. This way I will have content scheduled and one goes out everyday. Back to today’s topic, we can start with running the indexer locally. To run ...

In the last article, I showed you how to create a new HyperIndex project, but I didn’t explain how it all fits together. Today, let’s create the project again and walk through its structure step by step. Create a New Project Open your terminal and run: pnpx envio init Answer the prompts as follows: Folder name: Press Enter to use the current directory. Language: Choose TypeScript (I prefer it, but JavaScript and ReScript are also supported). VM type: Select EVM (Across Protocol is deployed on EVM chain...