HF Model & Benchmark Matrix
Overview
Benchmarks
Speech
Models
Orgs
24,078 variants · 14,984 scores · 120 benchmarks
Home
/
Models
/
inclusionAI/VISTA-4B
VISTA-4B
inclusionAI/VISTA-4B
kind
original
quant
bf16 (16-bit)
family
misc
modality
image-text-to-text
root model
inclusionAI/VISTA-4B
provider
inclusionAI
license
apache-2.0
language
en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
113
likes
7
created
—
last modified
2026-06-15T01:26:24+00:00
(2026)
huggingface
https://huggingface.co/inclusionAI/VISTA-4B
tags
transformers
safetensors
qwen3_5
image-text-to-text
vista
qwen3.5
vision-language
gui-grounding
reinforcement-learning
conversational
en
arxiv:2606.14579
license:apache-2.0
endpoints_compatible
region:us
Benchmark scores (1)
benchmark
category
score
context
conf
evidence
OSWorld
agentic
54.4
low
| Qwen3.5-4B | 60.3 | 90.4 | 54.4 | 66.8 |
Discussions (0)
none scraped.
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.