---
title: "Vedant Jadhav (@vedantjadhav) | Hashnode"
description: "AI/ML Engineer exploring LLMs, Edge AI, and AI infrastructure. Read the latest articles by Vedant Jadhav on Hashnode."
url: "https://hashnode.com/@vedantjadhav"
---

@vedantjadhav

# Vedant Jadhav

@vedantjadhav · Pune, India · Joined October 2026

AI/ML Engineer exploring LLMs, Edge AI, and AI infrastructure

## Comments

[Thanks Ahmed. Very useful point. I agree that nearby configuration splits can overstate generalization. I’ll add grouped holdout experiments (model size / precision / backend) alongside the current validation, and introduce an explicit “outside coverage” signal for extrapolated predictions. This should make the uncertainty and deployment layer more rigorous.](https://hashnode.com/posts/amd-llm-lab/6ac15c1df8437aace82ad975/comment/6ac2939c02c54c62417e0a05#reply-6ac2990f3d5c6f121817079a)

Reply · Article · Oct 4 · 1 · [What 57 LLM Benchmark Runs on an AMD Instinct MI300X Taught Me About VRAM, Throughput, and Quantization](https://hashnode.com/posts/amd-llm-lab/6ac15c1df8437aace82ad975)