Discover Arcee AI: Spotlight Vision-Language Model

Spotlight excels in image-text grounding with fast, accurate results.

Input: image · text Output: text Context: 131,072 tokens Release: 2025-05-05

Arcee AI: Spotlight, released in May 2025, is a vision-language model designed for tasks that require tight image-text grounding. With a 32k-token context window, it facilitates rich multimodal conversations by seamlessly integrating lengthy documents with images. Developed from Qwen 2.5-VL and fine-tuned by Arcee AI, it excels in captioning, visual question answering, and diagram analysis. Spotlight's design ensures fast inference on consumer GPUs, making it ideal for workflows involving screenshots, charts, or UI mock-ups. It supports input modalities of text and images, producing text outputs, and has shown strong performance in early benchmarks.

Use Cases

Here are a few ways teams apply Arcee AI: Spotlight in practice—from fast drafting to multimodal understanding. Adapt these ideas to your workflow.

Interpret screenshots and charts quickly

Engage in rich multimodal conversations

Analyze diagrams with precision

Enhance visual question answering tasks

Key Features

A quick look at the capabilities that make this model useful in real projects.

7-billion-parameter model

32k-token context window

Fast inference on consumer GPUs

Strong visual question answering

Effective diagram analysis

Multimodal conversations

Specs

Overview

Vendor
arcee-ai

Model ID
arcee-ai/spotlight

Release
2025-05-05

Modalities & context

Input
image · text

Output
text

Context
131,072 tokens

Parameters & defaults

Supported parameters: frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, stop, temperature, top_k, top_p

Defaults: temperature 0.2, top_p 0.95

Benchmark tests: Arcee AI: Spotlight

We ran this model against a few representative prompts to show its range. Review the outputs below and be the judge.

Text

Prompt:

Write 150 words on how AI might positively upend work, leisure and creativity

Preview unavailable.

Run this prompt on Upend.AI

Image

Prompt:

Generate an SVG of a pelican riding a bicycle.

Run this prompt on Upend.AI

Ready to try Arcee AI: Spotlight?

Chat with Arcee AI: Spotlight

up.end

/ˌəpˈend/

verb

To “upend” means to completely disrupt, overturn, or drastically change the established order or structure of something. It implies a significant shift or alteration that can potentially have far-reaching consequences. When something is upended, it is turned upside down or transformed in a way that challenges conventional norms or expectations. The term often carries a sense of innovation, transformation, and sometimes even a hint of upheaval, indicating that the changes are not just minor adjustments but rather a fundamental reimagining of the status quo.

Privacy Terms