C4AI Aya Vision 32B

Name: C4AI Aya Vision 32B
Author: CohereAI

Multimodal modelC4

C4AI Aya Vision 32B

Release date: 2025-03-04Updated: 2025-03-04Views: 733

Live demoGitHub Hugging Face Compare

Parameters

32B

Context length

16K

Multilingual

Supported

Reasoning ability

No data

C4AI Aya Vision 32B is an AI model published by CohereAI, released on 2025-03-04, for Multimodal model, with 32B parameters, and 16K context length, requiring about 64GB storage, with a 72.14 score on MMLU.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

C4AI Aya Vision 32B

Model basics

Reasoning traces

No data

Thinking modes

Thinking modes not supported

Context length

16K tokens

Max output length

No data

Model type

Multimodal model

Modality (in / out)

Text, Image → Text

Release date

2025-03-04

Model file size

64GB

MoE architecture

Total params / Active params

32B / Not applicable

Knowledge cutoff

No data

C4AI Aya Vision 32B

Open source & experience

Code license

Weights license

- Non-commercial only

GitHub repo

github.com/huggingface/blog/blob/main/aya-visio…

Hugging Face

huggingface.co/CohereForAI/aya-vision-32b

Live demo

N/A

C4AI Aya Vision 32B

Official resources

Paper

DataLearnerAI blog

N/A

C4AI Aya Vision 32B

API details

API speed

No data

No public API pricing yet.

C4AI Aya Vision 32B

Benchmark Results

C4AI Aya Vision 32B currently shows benchmark results led by MBPP (34 / 96, score 70.43), HumanEval (69 / 140, score 62.20), MATH (21 / 42, score 69.30). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.