LLM Reference

Arcee Spotlight Models by Arcee AI

Arcee AIApache 2.0Open source
1 model2025Up to 128k ctx

Details

ResearcherArcee AI
LicenseApache 2.0(OSI)
Commercial useCommercial use allowed
Models1
Released2025
Max context128k

Capabilities

VisionAll models
MultimodalAll models
Function CallingAll models
Tool UseAll models
Structured OutputsAll models

Links

Website

About

Arcee AI Spotlight is a 7B vision-language model derived from Qwen 2.5-VL, fine-tuned for tight instruction following in multimodal tasks.

Current Variants

Use-when guidance is derived from seed capabilities, context, release, and replacement fields.

1 in view

Use when the workload needs 128k context, 7B parameters, and tool use.

2025-12128k context7B parameterstool use

Release Timeline

1 release group
2025-12
1 current
Arcee Spotlight
128k context7B parameterstool use
Current

Specifications(1 models)

Arcee Spotlight model specifications comparison
ModelReleasedContextParametersVisionMultimodalFn CallingTool UseStructured Outputs
Arcee Spotlight2025-12128k7BYesYesYesYesYes

Frequently Asked Questions

What is Arcee Spotlight used for?
Arcee Spotlight is used for vision and multimodal work, agent workflows and tool use, and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
How does Arcee Spotlight compare to AFM?
Arcee Spotlight by Arcee AI is strongest where you need vision and multimodal work, while AFM by Arcee AI is the closest related family to check for adjacent model selection. Arcee Spotlight has 1 listed variant and reaches up to 128k context, while AFM reaches up to 66k context, so compare the specs and pricing tables before choosing a production model.
Which Arcee Spotlight model should I use?
If price is the main constraint, use the pricing table first because Arcee Spotlight does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Arcee Spotlight with 128k context and tool use, function calling, structured outputs, and multimodal inputs.