Liquid AI Open-Sources d1 Decision Models Running in a Single Forward Pass on NVIDIA Jetson
JosephJacks_ · x · 2026-10-08
- Liquid AI announced a partnership with NVIDIA Robotics and open-weighted two "decision models": d1-3B and d1-omni-600M.
- Both models deliver answers in a single forward pass on NVIDIA Jetson Thor, Jetson AGX Orin, and Orin Nano, targeting low-latency on-device inference.
- NVIDIA officially congratulated Liquid AI and pointed developers to the Jetson AI Lab for instructions on running the models at the edge.
Related event: Liquid AI Open-Sources d1 Decision Models for Millisecond Edge Inference(11 posts)→
More from Infra
- Blockway Ships Agens Volundr 32B: Only 18 Layers Keep KV Cache for Long Context — lmoroney · 2026-10-08
- Yaroslav Bulatov Traces the Origins of the Memory Wall in New Research Writeup — yaroslavvb · 2026-10-08
- Two Years Building a Local Agent OS: Multi-Node Routing, Memory Arbitration and Failure Governance — Budget_One_8784 · 2026-10-08
- DARPA QBI finalists revealed: six quantum approaches, up to $300M each through 2029 — hardimanjames · 2026-10-08
- DCVC recalls backing Atom Computing from pitch deck to DARPA QBI finalist — hardimanjames · 2026-10-08
- Rust+Vulkan Inference Backend Goes Cross-Vendor: Pick Kernels by CPU ISA, Not GPU Vendor — PhysicsDisastrous462 · 2026-10-08