← Back to Hugging Face models & datasets

Top Hugging Face models and datasets by download growth, 3 November 2026

The top 5 Hugging Face models and datasets by download growth over the 1-day window ending 3 November 2026, measured by RiseFinder.

Period
Daily
Window
1 day
Rows
5
Data through
3 November 2026
← All current risersAll Hugging Face models and datasets editionsNewer: 4 November 2026Older: 2 November 2026

At a glance

Hugging Face Models & Datasets: 3 November 2026: rank, name, readings and change
RankNameBefore → afterChange
1moondream/refcoco-m1,046 → 1,249 downloads+19.4%
2LiquidAI/LFM3-Omni-2B8,376 → 9,964 downloads+19%
3hongzhuyi/VDEBench6,305 → 6,995 downloads+10.9%
4RecursiveSI/flint26,703 → 29,574 downloads+10.8%
5jialinyyzz/humanizer264,723 → 281,010 downloads+6.2%
01/

Daily box

5 entries
01

moondream/refcoco-m

This dataset serves as a benchmark for referring expression segmentation. While it has historically been a standard benchmark, the evidence notes that it contains issues such as poor mask quality and harmful referring expressions. Furthermore, modern models are capable of producing masks that are more accurate than the ground-truth annotations provided in the dataset, which suggests the dataset may be an imprecise measure.

Hugging Face dataset

Open source ↗
+19.4%
1,046 → 1,249 downloads
02

LiquidAI/LFM3-Omni-2B

LiquidAI/LFM3-Omni-2B is an AI model that handles multiple kinds of input and output in a single system. It understands text, images, video and audio, and responds in text or speech. It is built for on-device use, replacing what would otherwise require a separate ASR model, vision-language model, LLM and TTS model.

Hugging Face model

Open source ↗
+19%
8,376 → 9,964 downloads
03

hongzhuyi/VDEBench

VDEBench is a bilingual benchmark dataset for visual document editing, containing 3,506 examples split into 1,578 text edits and 1,928 table edits. Each example provides the input document image, an editing instruction, a target image, editing-region annotations, and recorded source provenance. Available masks indicate which regions of a document are allowed for editing.

Hugging Face dataset

Open source ↗
+10.9%
6,305 → 6,995 downloads
04

RecursiveSI/flint

Flint is a mixture-of-experts language model made by Recursive for use with coding agents. It has 39.8 billion total parameters with approximately 2.5 billion active per token. It is designed for software engineering work such as investigating codebases, fixing bugs, implementing features, and writing tests.

Hugging Face model

Open source ↗
+10.8%
26,703 → 29,574 downloads
05

jialinyyzz/humanizer

jialinyyzz/humanizer is a 12B language model that rewrites AI-written drafts such as emails, essays, reports, and forum posts in English and Chinese so they read like a person wrote them. It is trained to keep every number, unit, date, name, and quote from the original text and to add nothing. The model runs locally, and no AI detector was used anywhere in its training.

Hugging Face model

Open source ↗
+6.2%
264,723 → 281,010 downloads
This dated edition is generated from the reviewed RiseFinder export. Movement figures retain their original source, period and direction.
02/

Get email updates

Join the list

Get early signals on the websites, apps, repositories and startups gaining momentum. Join the list for RiseFinder email briefings.

By subscribing, you ask us to store your email and send Risefinder updates. You can unsubscribe at any time. Privacy.

Want a sample first? Read past daily emails.