Skip to content

Trending AI Today

LiquidAI/LFM3-1.7B

Model · Text generation · edition of October 29, 2026

LiquidAI/LFM3-1.7B is a text generation model published by LiquidAI on Hugging Face, a fine-tune of LiquidAI/LFM3-1.7B-Base. At the collection of October 29, 2026 it was No. 6 on the trending list, with 8,892 downloads in 30 days and 420 likes.

Collected · snapshot shipped with the site build, not a live feed

Why it is on the list

  • No. 6 by Hugging Face trending score (416)
  • repository created 5 days ago
  • +23 likes since 2026-10-28

8,892downloads in 30 days

420likes

Since October 28, 2026: +0 downloads (30-day figure), +23 likes

Positions and counts are Hugging Face’s; we report them and add no score of our own.

Open on Hugging Face (opens in a new tab)

Source: Hugging Face public API · updated

Fact sheet

Licence
Other (custom terms) · Read the termsCustom or use-restricted terms (for example OpenRAIL, Llama, Gemma or a vendor licence). Read the licence text before commercial use.
Size
1,728,801,536 parametersAbout 3.5 GB of weights at 16 bits; about 1.0 GB at a typical 4-bit quantisation.
Formats and library
safetensors, transformers
Fine-tune of
LiquidAI/LFM3-1.7B-Base (opens in a new tab)
Access
Open download
Created · last changed
·
Downloads, all time
8,892

Most downloaded quantisations

Repositories that declare this model as base

Questions about LFM3-1.7B

Why is LiquidAI/LFM3-1.7B trending?

No. 6 by Hugging Face trending score (416); repository created 5 days ago; +23 likes since 2026-10-28. Hugging Face does not publish the formula of its trending score; these are the public figures behind the position.

Can LFM3-1.7B be used commercially?

The repository is tagged with the licence "Other (custom terms)". Custom or use-restricted terms (for example OpenRAIL, Llama, Gemma or a vendor licence). Read the licence text before commercial use. The tag is set by the uploader, so confirm it against the licence file in the repository.

How large is LFM3-1.7B?

1.73B parameters according to the safetensors metadata. Weights alone take about 3.5 GB at 16 bits per parameter and about 1.0 GB in a typical 4-bit quantisation, before the memory needed for the context.

Are there quantised versions of LFM3-1.7B?

Yes. The most downloaded repositories that declare LiquidAI/LFM3-1.7B as their base are LiquidAI/LFM3-1.7B-GGUF (18.2K downloads in 30 days), AtomicChat/LFM3-1.7B-Uncensored-GGUF (2,317 downloads in 30 days), AtomicChat/LFM3-1.7B-GGUF (2,104 downloads in 30 days).