web02.fireside.fm Sat, 11 Apr 2026 10:31:16 -0500 Fireside (https://fireside.fm) Coder Radio - Episodes Tagged with “Local Llms” https://coder.show/tags/local%20llms Wed, 08 Apr 2026 05:00:00 -0400 A weekly talk show taking a pragmatic look at the art and business of Software Development and the world of technology. en-us episodic A weekly talk show The Mad Botter A weekly talk show taking a pragmatic look at the art and business of Software Development and the world of technology. no The Mad Botter michael@themadbotter.com 645: Warp's Holmes & Llyod https://coder.show/645 78060061-1ba3-43a5-b70b-4da3abc9d24e Wed, 08 Apr 2026 05:00:00 -0400 The Mad Botter full The Mad Botter A rare trio episode with two of luminaries behind Warp and good old gungan Mike where they discuss all things agentic including Warp's very own Oz. 27:06 no Warp's Oz (https://www.warp.dev/oz) Ben on LinkedIn (https://www.linkedin.com/in/bholmesdev/) Zach on LinkedIn (https://www.linkedin.com/in/zachlloyd/) Coder Radio Discord (https://discord.gg/k8e7gKUpEp) The Mad Botter Data Platform (https://themadbotter.com/botterkit) Mike's Blog (https://dominickm.com) ai, programming, nosql, linux, bigdata, bi, rust, dotnet, node, ruby, tabnine, coding, vibe coding, co-pilot, warp, agentic, agents, ai Warp's Oz
Ben on LinkedIn
Zach on LinkedIn

Coder Radio Discord
The Mad Botter Data Platform
Mike's Blog

]]> Warp's Oz
Ben on LinkedIn
Zach on LinkedIn

Coder Radio Discord
The Mad Botter Data Platform
Mike's Blog

]]> 636: Red Hat's James Huang https://coder.show/636 21937e2f-637d-493a-88a8-90e81c016e7c Fri, 19 Dec 2025 04:00:00 -0500 The Mad Botter full The Mad Botter In this episode of the Coder Radio (Coder.show) network, Michael Dominick sits down with James Huang, Senior Product Manager of AI and High Performance Computing at Red Hat, to discuss the intersection of enterprise-grade Linux and the rapidly evolving world of artificial intelligence. 20:53 no Links James on LinkedIn (https://www.linkedin.com/in/jahuang/) Mike on LinkedIn (https://www.linkedin.com/in/dominucco/) Mike's Blog (https://dominickm.com) Show on Discord (https://discord.com/invite/k8e7gKUpEp) Alice Promo (https://go.alice.dev/data-migration-offer-hands-on) AI on Red Hat Enterprise Linux (RHEL) Trust and Stability: RHEL provides the mission-critical foundation needed for workloads where security and reliability cannot be compromised. Predictive vs. Generative: Acknowledging the hype of GenAI while maintaining support for traditional machine learning algorithms. Determinism: The challenge of bringing consistency and security to emerging AI technologies in production environments. Rama-Llama & Containerization Developer Simplicity: Rama-Llama helps developers run local LLMs easily without being "locked in" to specific engines; it supports Podman, Docker, and various inference engines like Llama.cpp and Whisper.cpp. Production Path: The tool is designed to "fade away" after helping package the model and stack into a container that can be deployed directly to Kubernetes. Behind the Firewall: Addressing the needs of industries (like aircraft maintenance) that require AI to stay strictly on-premises. Enterprise AI Infrastructure Red Hat AI: A commercial product offering tools for model customization, including pre-training, fine-tuning, and RAG (Retrieval-Augmented Generation). Inference Engines: James highlights the difference between Llama.cpp (for smaller/edge hardware) and vLLM, which has become the enterprise standard for multi-GPU data center inferencing. Artificial Intelligence & Machine Learning, Open Source Software, AI, FOSS, Cloud Native & Containers Links
James on LinkedIn
Mike on LinkedIn
Mike's Blog
Show on Discord

Alice Promo

  1. AI on Red Hat Enterprise Linux (RHEL)

Trust and Stability: RHEL provides the mission-critical foundation needed for workloads where security and reliability cannot be compromised.

Predictive vs. Generative: Acknowledging the hype of GenAI while maintaining support for traditional machine learning algorithms.

Determinism: The challenge of bringing consistency and security to emerging AI technologies in production environments.

  1. Rama-Llama & Containerization

Developer Simplicity: Rama-Llama helps developers run local LLMs easily without being "locked in" to specific engines; it supports Podman, Docker, and various inference engines like Llama.cpp and Whisper.cpp.

Production Path: The tool is designed to "fade away" after helping package the model and stack into a container that can be deployed directly to Kubernetes.

Behind the Firewall: Addressing the needs of industries (like aircraft maintenance) that require AI to stay strictly on-premises.

  1. Enterprise AI Infrastructure

Red Hat AI: A commercial product offering tools for model customization, including pre-training, fine-tuning, and RAG (Retrieval-Augmented Generation).

Inference Engines: James highlights the difference between Llama.cpp (for smaller/edge hardware) and vLLM, which has become the enterprise standard for multi-GPU data center inferencing.

]]> Links
James on LinkedIn
Mike on LinkedIn
Mike's Blog
Show on Discord

Alice Promo

  1. AI on Red Hat Enterprise Linux (RHEL)

Trust and Stability: RHEL provides the mission-critical foundation needed for workloads where security and reliability cannot be compromised.

Predictive vs. Generative: Acknowledging the hype of GenAI while maintaining support for traditional machine learning algorithms.

Determinism: The challenge of bringing consistency and security to emerging AI technologies in production environments.

  1. Rama-Llama & Containerization

Developer Simplicity: Rama-Llama helps developers run local LLMs easily without being "locked in" to specific engines; it supports Podman, Docker, and various inference engines like Llama.cpp and Whisper.cpp.

Production Path: The tool is designed to "fade away" after helping package the model and stack into a container that can be deployed directly to Kubernetes.

Behind the Firewall: Addressing the needs of industries (like aircraft maintenance) that require AI to stay strictly on-premises.

  1. Enterprise AI Infrastructure

Red Hat AI: A commercial product offering tools for model customization, including pre-training, fine-tuning, and RAG (Retrieval-Augmented Generation).

Inference Engines: James highlights the difference between Llama.cpp (for smaller/edge hardware) and vLLM, which has become the enterprise standard for multi-GPU data center inferencing.

]]> 563: Mike’s No Good Very Bad Rails Update https://coder.show/563 c669af7a-33d8-4516-97f8-6998a9def884 Wed, 27 Mar 2024 06:00:00 -0400 The Mad Botter full The Mad Botter Mike makes the case for just going vanilla, a look at Google Carbon, and then we address the expensive elephant in the room. 57:16 no Mike makes the case for just going vanilla, a look at Google Carbon, and then we address the expensive elephant in the room. Coder Radio, Development Podcast, developers, Google Carbon, expensive elephant, 3 Body Problem, Netflix, Feedback, Apple, WWDC 2024, RCS support, iPhon, Apple Developer, YouTube, text editor, Helix, Rails, Asset Pipeline, vanilla JS, importmap-rails, ESM, LM Studio, local LLMs, HuggingFace, NOSTR, Google Carbon, C++ successor, C++ interop, Github, Apple Vision Pro, XR, NVIDIA, AI, Barbara Fried, SBF, sentencing submission Mike makes the case for just going vanilla, a look at Google Carbon, and then we address the expensive elephant in the room.

Sponsored By:

Links:

]]> Mike makes the case for just going vanilla, a look at Google Carbon, and then we address the expensive elephant in the room.

Sponsored By:

Links:

]]>