Skip to content

William Denniss

  • Blog
  • Book
  • Tweets
  • LinkedIn

Tag: llm

Running DeepSeek open reasoning models on GKE

DeepSeek’s R1 open model launch caused quite a stir with one of the first open reasoning models. Here’s how to run a demo of it locally on GKE! We can use an Nvidia L4 (or A100 40GB) to run the 8B Llama distilled model, or a A100 80GB to run the 14 and 32B Quen… Continue reading Running DeepSeek open reasoning models on GKE

Published February 26, 2025
Categorized as Autopilot Tagged ai, autopilot, GKE, llm

Recent Posts

  • Trying out C4A and C4D with Compute Class
  • Simulate a zonal failure on Autopilot
  • Running Docker in Docker on GKE Autopilot with gVisor
  • Running DeepSeek open reasoning models on GKE
  • Kubernetes History Inspector
  • Save 35% off my book Kubernetes for Developers
William Denniss
Proudly powered by WordPress.