Amir Haghighat's videos and podcasts

Build a chatbot with Llama 2 and LangChain

Joey Zwicker joins Baseten as Head of FDE

Pinning ML model revisions for compatibility and security

NVIDIA Nemotron 3 Super for agentic AI in financial services

Introducing the Baseten Delivery Network: Fast cold starts for big models

A guide to LLM inference and performance

A guide to LLM inference and performance

Ian Carrasco - Forward Deployed Engineer

Max Kirkby - Post-Training Team

Building AI Agents, Open Code, and Open Source Coding with Dax Raad

Glossary

Blog

Where to run your inference workloads

Guides

Aaron Relph - Design Lead

The complete DeepSeek model guide

Guides

Resources

Mistral Large 3 2512

Model library

The complete DeepSeek model guide

Guides

Justin Yi - Software Engineer

Suren Atoyan - Software Engineer

Qwen3 TTS 12Hz Base Streaming 1.7B

Model library

Startup Program legal disclaimers

Mahmoud Hassan - Model Performance Engineer

Chinmayee Kulkarni - Chief of Staff Intern @ Patronus AI

MiniMax M2.5

Model library

Nilesh Agarwal - Infrastructure Engineer

NVIDIA Nemotron 3 Nano

Model library

Continual learning and the post monolith AI era

Towards infinite context windows: neural KV cache compaction

33% faster LLM inference with FP8 quantization

Baseten brand guidelines