Liquid LFM3 — local AI model by Liquid AI
Written by Jakub Rusinowski · Last updated
Liquid AI's third-generation edge models, announced on 27 October 2026: a tri-hybrid of gated short convolutions, sliding-window and global attention, so only a quarter of the layers keep a full-length cache. The text model fits in about 1 GB at 4-bit. LFM Open License v1.0: commercial use is free below US$10M annual revenue.
Variants
The smallest Liquid LFM3 variant needs about 2 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| LFM3 1.7B → 1.7B | ~1.8 GB | 262,144 | ollama run lfm3:1.7b | |
| LFM3-VL 2B → 2B | ~2 GB | 128,000 | cloud-hosted tag |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Liquid LFM3 locally
Install Ollama, then pull the tag.
ollama run lfm3:1.7bPick 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: LFM3 1.7B, LFM3-VL 2BRecommended GPU
The cheapest catalogued GPU that runs Liquid LFM3 locally (min 2 GB VRAM) is the Intel Arc B570 (10 GB).
Liquid LFM3 — frequently asked questions
How much VRAM does Liquid LFM3 need?
Liquid LFM3 needs about 2 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: LFM3 1.7B (2 GB, Q4_K_M); LFM3-VL 2B (2 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Liquid LFM3 on an RTX 4090 (24 GB)?
Yes — Liquid LFM3 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 Liquid LFM3?
Q4_K_M is the best balance of quality and VRAM for Liquid LFM3 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 Liquid LFM3 with Ollama?
Install Ollama, then run: ollama run lfm3:1.7b. This downloads Liquid LFM3 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.