Sveriges mest populära poddar

Mixture of Experts at the Edge: Running 30B Parameter Models on Your Laptop

21 min•16 juli 2026

Om avsnittet

A 30B parameter model runs on a MacBook because only 3B parameters fire per token. Mixture of Experts splits memory cost from compute cost, and that changes everything about where AI can run.

Fler avsnitt

The Agent Interoperability Problem: Why Your AI Agents Can Not Talk to Each Other

2 juli22 min

KV Cache Compression: The Memory Wall Nobody Talks About

18 juni22 min

Context Rot: Why Million-Token Windows Quietly Fail

4 juni21 min

LLMOps: Operating Large Language Models in Production

26 maj28 min

TinyML & Edge AI: Machine Learning on Devices

12 maj26 min

AI Hardware: GPUs, TPUs and Beyond

28 apr.26 min

The Practical AI Digest med Mo Bhuiyan finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.

Mixture of Experts at the Edge: Running 30B Parameter Models on Your Laptop

Om avsnittet

Fler avsnitt

Retrieval-Augmented Generation Is Broken: How to Fix It

Distillation: How Small Models Eat Big Models for Lunch

World Models: When AI Learns Physics Instead of Memorizing Data

The Evaluation Crisis: We Do Not Know How Good Our Models Actually Are