YHK - yet another hacker news clone

Introducing LFM3: Every Modality for Specialized Intelligence

42 points Philpax 2 hours ago 13 comments

Philpax 2 hours ago | parent

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

pember 2 hours ago | parent

Title is: Introducing LFM3: Every Modality for Specialized Intelligence

Philpax 2 hours ago | parent

updated, ty

samstevens 1 hour ago | parent

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

hypfer 1 hour ago | parent

In a few words: Why should I care about this?

What makes it cool? What should make me go "oh yeah let's go"?

From what I can see by skimming the document, I would assume "something something specialized use-cases", but what does that mean? And what does it mean assuming I have attention deficit?

samstevens 1 hour ago | parent

Depends on what you care about.

If you want to do local classification/image processing, I think the d1-2B is amazing, it can run on 1GB of unified RAM.

Now that it's released and I have weekends off again, I'm going to play with the VL-2B model and the d1-2B and see if I can prompt it to control a small Lego robot arm like this https://bricksrl.github.io/ProjectPage/

If you like agents, I think the 1.7B is very strong for its size and can be used to automate small stuff like classifying emails, cleaning your downloads folder, etc.

It can also be fine-tuned for specific use cases with SFT/DPO/GRPO. The blog post talks about fine-tuning for wind-turbine classification. If there's things you want to automate, but GPT-6-Luna is not strong enough, and bigger models are too expensive, you might fine-tune one of the LFM3 models and use it locally for repetitive tasks.

colingauvin 1 hour ago | parent

No weekends. We need you to get back to work on the next 8B.

Powdering7082 19 minutes ago | parent

I am seeing the following in the reasoning trace:

> However, the instructions say I must use available tools when answering questions.

On "What animal lays the biggest egg?" with no system prompt

I assume this is something baked into the model through lots of RL with tool use?

colingauvin 1 hour ago | parent

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.

pritambaral 54 minutes ago | parent

Have you considered fine-tuning on your dataset?

colingauvin 46 minutes ago | parent

Seeing the fine-tuning guides that are coming out with LFM3, I am now considering it :)

Would be a fun experiment.

jauntywundrkind 49 minutes ago | parent

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 9 minutes ago | parent

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.