Skip to content
Sign in
Artwork for Neural intel Pod
Neural intel Pod · July 16 · 50 min

Inside Inkling’s 1T MoE Architecture and 1M Token Context

The era of "proprietary-only" frontier intelligence is over. The Problem: Western developers have been forced to rely on Chinese models like Qwen or Kimi for high-performance open-weights alternatives while Meta’s Llama 4 pivots toward proprietary paths. The Solution: Inkling—a sparse Mixture-of-Experts (MoE) transformer with 256 routed experts designed for sovereignty and auditability. In this episode, we go under the hood of Thinking Machines’ first release. We discuss: Give us your take in the comments below: Is a 1T open-weights model the moat your infrastructure has been waiting for? Follow us on X: @neuralintelorg Join the community: neuralintel.org

0:00-50:06
Play in

transcript

No transcript — this publisher did not publish one.

show notes

    • The era of "proprietary-only" frontier intelligence is over. The Problem: Western developers have been forced to rely on Chinese models like Qwen or Kimi for high-performance open-weights alternatives while Meta’s Llama 4 pivots toward proprietary paths. The Solution: Inkling—a sparse Mixture-of-Experts (MoE) transformer with 256 routed experts designed for sovereignty and auditability.
    • In this episode, we go under the hood of Thinking Machines’ first release. We discuss:
    • Give us your take in the comments below: Is a 1T open-weights model the moat your infrastructure has been waiting for?
links2

more episodes

All episodes