d1 — local AI model by Liquid AI
Written by Jakub Rusinowski · Last updated
Liquid AI's edge decision models: d1-3B (text and images, on LFM2.5-VL-3B) and the experimental d1-omni-600M (text with images or audio). A Python library loaded through Transformers, not a server; released under the LFM Open License v1.0.
Variants
The smallest d1 variant needs about 1 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| d1-3B → 3B | ~2.7 GB | 32K (32,768) | Transformers (trust_remote_code) | |
| d1-omni-600M → 600M | ~1.2 GB | 16K (16,384; 896 text tokens with images) | Transformers (trust_remote_code) |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run d1 locally
Install Ollama, then pull the tag.
A Python library: you load it inside your own program. It has no HTTP server and does not run in Ollama.
Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Applies to: d1-3B, d1-omni-600MRecommended GPU
The cheapest catalogued GPU that runs d1 locally (min 1 GB VRAM) is the Intel Arc B570 (10 GB).
d1 — frequently asked questions
How much VRAM does d1 need?
d1 needs about 1 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: d1-3B (3 GB, Q4_K_M); d1-omni-600M (1 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run d1 on an RTX 4090 (24 GB)?
Yes — d1 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for d1?
Q4_K_M is the best balance of quality and VRAM for d1 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run d1 locally?
d1 is a decision model: it is called over an HTTP endpoint (/v1/systemone), not chatted with. Where a variant is available in Ollama 0.35 or newer, pull it with `ollama pull` and send requests to the local server; the others ship their own server. Each variant page shows the exact commands for that model.