Skip to main content

AI news

Hao AI Lab releases faster open Pika H3 Flex inference and quantized weights

UC San Diego’s Hao AI Lab released FastVideo inference and NVFP4 quantized weights for Pika H3 Flex on November 3. The lab reports up to sevenfold faster generation on specified Blackwell GPUs; performance on smaller machines differs. MiniMax made the underlying H3 model and Pika post-trained H3 Flex. This is a new optimization and weight artifact, not a newly trained Pika model.

Hao AI Lab

Pika H3 Flex FastVideo

Tools & Agents

Published (date only)

Updated

1 source

Primary source · Hao AI Lab / UC San Diego · November 3, 2026

Opens Hao AI Lab / UC San Diego in a new tab. Read it there before you rely on the summary above.

Read the original

Free, email only

Unlock the full brief free.

  • What to check before you trust this story, written down
  • Each verified source, with why it matters and who published it
  • A note whenever a source has been withdrawn
  • Thirty days of stories to browse, not seven
Continue with Google and subscribeContinue with Apple and subscribe

Continuing subscribes the email on that account to Work Worth Doing, my newsletter, the same as the form below, and unlocks every free tool in this browser. We only receive your email address. Unsubscribe in one click.

This is not an account: there is no password, and the unlock is a cookie in this browser. You also join Work Worth Doing, Demetri Panici's newsletter, every week: what I built and what changed in AI. We'll email you a link to confirm, and you can unsubscribe in one click. The same signup unlocks every free tool on the site. How your email is handled.

Already subscribed? Enter the same email to unlock this browser. You won't be signed up twice.