GTA1-32B

HelloKKMe· 04 Jun 2025

Multimodal

A GUI grounding model to detect the location of objects in (computer) screens. Despite the name, it has no relation to R1 other than the training style. Their blog post goes into more detail.

Specs

Params32B

LicenseUnknown

Tags

models/llms/multi-modal

Similarity · VAIL

VAIL Fingerprint

003b:0049:0060:0073:00d8:01c6:06ab:5f89

Explore other models with behavioral similarity to GTA1-32B.

Resources

Hugging Face — HelloKKMe/GTA1-32B Paper / tech report Appeared in Artifacts Log #11

How these metrics work

Adoption · Hugging Face

RAM score

—

Hugging Face Downloads

last 30d

15.1K

all time

HF Likes

Relative Adoption Metric contextualizes downloads against the model's size bucket.

Related Models

Similar Models

Qwen2.5-VL-32B-Instruct

Qwen21 Mar 2025

shared lineagemultimodal32B params

Skywork-R1V2-38B

Skywork22 Apr 2025

shared lineagemultimodal38B params

Qwen3-Omni-30B-A3B-Instruct

Qwen22 Sep 2025

multimodal30B params

Mistral-Small-3.2-24B-Instruct-2506

Mistral19 Jun 2025

multimodal24B params