Hugging Face models & datasets

The top 5 hugging face models & datasets measured by RiseFinder over the 1d window ending 22 October 2026.

Period
Daily
Window
1d
Rows
5
Data through
22 October 2026
← All current risersAll hugging face models & datasets editionsOlder: 21 October 2026
01/

Daily box

5 entries
01

vllm-sr/d3-turbo

vllm-sr/d3-turbo is an upgraded 27B multimodal decision model. It accepts input in text or JSON format, and optionally includes images and videos. The model processes this input to answer specific questions or requests. It can instruct the user to pick one of several options, say yes or no, rate on a scale, or point to where.

Hugging Face model

Open source ↗
+93%
300 → 579 downloads
02

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 ↗
+19.3%
1,645 → 1,963 downloads
03

LiquidAI/LFM2.5-24B-A2B

LiquidAI/LFM2.5-24B-A2B is a reasoning model built for fast, private agents that operate on-device. It is characterized as a 24B-parameter model that utilizes only 2B active parameters. This model represents the largest and final iteration within the LFM2.5 family. Its design focuses on providing efficient, private AI capabilities for local deployment.

Hugging Face model

Open source ↗
+9.9%
15,410 → 16,939 downloads
04

vllm-sr/d3

vllm-sr/d3 is a 27B multimodal foundation decision model, part of Decision 3.0, the decision models of vLLM Semantic Router. It takes an input in text or JSON form, optionally with images and videos, together with questions to answer. It can pick one of several options, say yes or no, or rate on a scale, and answers all of the questions it is given.

Hugging Face model

Open source ↗
+9.2%
5,458 → 5,959 downloads
05

Cactus-Compute/whistle

Cactus-Compute/whistle is a speech-to-text model designed for mobiles, wearables, robots, smart home devices, automotive systems, and microcontrollers. The whole model is a single 16.9 MB file. It runs on the same CPU engine as Needle, from the same container and the same quantisation, with no dependencies and no GPU.

Hugging Face model

Open source ↗
+6.3%
44,567 → 47,387 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.