Introducing LFM3: Every Modality for Specialized Intelligence

Philpax

Post not up yet, but the models are: https://huggingface.co/collections/LiquidAI/lfm3

samstevens

I worked on this release, happy to answer questions/chat about local AI vs cloud frontier models.

colingauvin

One thing I have been using LFM 2.6 for is annotating emails, text messages, and other metadata. I keep it all ingesting into one giant database and annotate it all as it comes in on an RTX A4500. The LFM annotations are basically triage, and then slowly annotations trickle into my halo model based on lowest confidence (right now that's DeepSeek 4.1 Flash 1017) for an upgraded annotation. (Agents can then search this database for context). Excited to roll out LFM 3 to replace it, looks like a big step up. Right now LFM 2.6 gets trustworthy annotations on just over 40% of data points. Just waiting for these to get into LocalAI.

jauntywundrkind

Agentic coding numbers on par with Qwen3.5-4B, the rest of the numbers on par with Qwen3.5-9B. Most impressive for a 1.7B model! Liquid has also been very good about keeping speed in mind, and the writeup here makes me expect similar. Really good stuff.

syntaxing

I’ve been using 2.6B as my main home assistant model and it’s been good. I switched to Ling 3.0 Tiny since it’s faster with A1B. Really hoping 1.7B is good enough (2.5 version was too dumb for HA) so I can run everything on one machine.

butternet

Loved playing with LFM2.5 and excited about this!

dchuk

Just tried both the Omni model and the text only model, both as mlx versions, in lm studio omlx and rapid mlx, none of them could actually fire the model up, kept saying safetensors cant be read (yes I realize Claude should hear this not this thread).

kooi

Looks really neat. I'm keen to try this on my clicks communicator when that arrives. It's mediatek NPU claims to handle ONNX. That plus the 12GB ram makes the wonder if I can get this phone to be a mini-agent.

good1andrew

has anyone tried finetuning one of these yet?

lubitelpospat

Surprisingly (or maybe not?), LFM3-VL-2B gave me better results than LFM3-1.7B on text-only prompts (general knowledge, chatting) through liquid playground. As an example, when asked “what does a cow say?”, LFM3-1.7B said that a cow can say “Oink”, and when I asked the same question to LFM3-VL-3B, it (correctly) said “moo”. I assume this is lower quant problem, though: Q8 versions I’ve played with through llama both give the correct “moo” answer.

yaoke259

First class hardware support makes this really exciting and different. On device processing is cheaper and faster, critical for real time applications of AI. Really excited for the rise of local, smart intelligence!