- Services
Liquid AI released d1-3B, an open-weight decision model that answers questions in a single forward pass without generating tokens. It accepts text, JSON, and images, and returns typed answers for yes/no, choice, and score questions. It has 3.12B parameters, a 32,768 token context length, and scores 48.57 on the Decision Index v0.2.1. It runs on NVIDIA GPUs and Jetson devices, with 8 ms latency on an RTX 4090. License is other.
A workable 3.12B-parameter dense decision model from Liquid AI. Treat the modality benchmarks above as the leading indicator of fit — composite scoring across modalities is still maturing. Newly released, so production-readiness is still being shaken out.
Generated from this model’s benchmarks and ranking signals. Editor reviews refine it over time.
Access model weights, configuration files, and documentation.
The top devices for this model at 4-bit, ranked by fit and speed.
| Device | Grade | VRAM |
|---|---|---|
| ACEMAGIC M1A Pro (i9-13900HK + ARC A770)ACEMAGIC | SS | 3.1 GB |
| Acer Veriton GN100 AI MiniAcer | SS | 3.1 GB |
| AMD Instinct MI300XAMD | SS | 3.1 GB |
| AMD Instinct MI325XAMD | SS | 3.1 GB |
| AMD Instinct MI355XAMD | SS | 3.1 GB |
Cheapest current cloud rentals with at least 3 GB VRAM, refreshed hourly.
Advertising disclosure: we earn commissions when you shop through the links below.
| Option | Cost / GPU-hour |
|---|---|
NVIDIA GeForce RTX 3060Vast.ai · Spot · 12 GB VRAM | $0.05 |
NVIDIA GeForce RTX 3060Vast.ai · On-Demand · 12 GB VRAM | $0.05 |
NVIDIA GeForce RTX 4060Vast.ai · Spot · 8 GB VRAM | $0.07 |
NVIDIA GeForce RTX 4060Vast.ai · On-Demand · 8 GB VRAM | $0.08 |
NVIDIA GeForce RTX 3070Vast.ai · Spot · 8 GB VRAM | $0.08 |
Per-GPU rate across RunPod, the Vast.ai marketplace, DigitalOcean, and Vultr.
Spot tier is interruptible. Plan for restarts when comparing against on-demand prices.
d1-3B is a 3B parameter decision model built on LFM2.5-VL-3B. It accepts a state (text, JSON, images, or a mix) and a set of questions, returning calibrated, typed answers in one forward pass with zero output tokens. It supports noul (yes/no), choice (one of named options), and score (2 to 10 ordered levels) question types. It has a 32,768 token context length and a SigLIP2 NaFlex shape-optimized 400M vision encoder. It is recommended for routing and triage, moderation, intent and topic classification, extraction checks, reranking, agent guardrails, and visual inspection. It is not a chat model and does not write text. It is available on Hugging Face under an 'other' license.
Explore the Provider
Aggregate stats, leaderboard, release timeline, and benchmark coverage across every Liquid AI model we track.
Check which of your devices can run this model and how fast.
Compare hosted per-token prices before you commit to local hardware.
Break-even math for self-hosting, renting a GPU, or paying per token.
Live status for the hosted APIs you might use instead of running this locally.
View on Hugging Face