# Liquid AI — Open d1: Edge decision models for text, vision, and audio

- Company: Liquid AI (liquid.ai)
- Announced: 2026-10-07
- Category: open-weight-release
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://www.liquid.ai/blog/d1-open
- Record: https://forck.live/items/16765-open-d1-edge-decision-models-for-text-vision-and-audio
- Subject: LFM / d1 models
- Open weights: yes
- Models affected: d1-3B, d1-omni-600M

Liquid AI released d1-3B and d1-omni-600M, two open-weight decision models that produce answers in a single forward pass. d1-3B scores 48.57 on the Decision Index v0.2.1, ahead of every model under 10B parameters, and runs on the full NVIDIA stack with latency as low as 8 ms on an RTX 4090. d1-omni-600M handles text, image, and audio inputs, scoring 15.95 on the same index.

## Evidence

Verbatim from https://www.liquid.ai/blog/d1-open:

> d1-3B scores 48.57 on the Decision Index v0.2.1 (public split), ahead of every model under 10B and on par with Decider 35B-A3B, a decision model 12x its size. It runs the full NVIDIA stack, from DGX in the data center to Jetson at the edge: d1-3B answers a question in 8 ms on an NVIDIA GeForce RTX 4090, 16 ms on a Jetson AGX Thor, and 26 ms on a Jetson AGX Orin.

---

Record: https://forck.live/items/16765-open-d1-edge-decision-models-for-text-vision-and-audio
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md