- Services
Liquid AI released d1-omni-600M, an experimental open-weight decision model built on the LFM2.5-Encoder-350M bidirectional encoder. It takes a state as text or JSON plus either images or up to 30 seconds of speech, and returns typed answers to yes/no, pick-one-of-named-options and ordered score questions in one forward pass with zero output tokens. It has 587M total parameters (381M shared trunk and decision head, 94M SigLIP2 vision encoder, 112M FastConformer audio encoder) and a 16,384 token context that covers text, image and audio positions together. Weights are on Hugging Face under a non-standard license and it scores 15.95 on Decision Index v0.2.1.
A workable 0.59B-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 | 0.9 GB |
| Acer Veriton GN100 AI MiniAcer | SS | 0.9 GB |
| AMD Instinct MI300XAMD | SS | 0.9 GB |
| AMD Instinct MI325XAMD | SS | 0.9 GB |
| AMD Instinct MI355XAMD | SS | 0.9 GB |
Cheapest current cloud rentals with at least 1 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-omni-600M is a 587M parameter decision model from Liquid AI's open d1 family. Questions follow the Decision Index schema with type, instructions and criteria, and each call returns typed answers plus input/output token usage where output tokens are always zero. It handles text and images or text and audio, not both in one request, and is not a chat model. Recommended uses include routing and triage, moderation, intent and topic classification, voice-command routing, extraction checks, reranking, agent guardrails and visual inspection.
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