All models

Aya Vision 8B

byCohereCohere· 02 Mar 2025
General purposeMultimodal

The first VLM release by Cohere, focusing on multilinguality. The model combines Cohere's Command R with SigLIP 2. Here's their win rate plot comparing peer models on multilingual, multimodal queries.

Specs
Params8B
LicenseCC-BY-NC-4.0
Tags
modelsmodels/llmsmodels/llms/multi-modalmultilingualartifacts/8
Adoption · Interconnects
RAM score
Hugging Face Downloads
159.2K
last 30d
1.2M
all time
HF Likes
322

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

VAIL
VAIL Fingerprint
0000:0000:0000:0002:001a:0204:1a7b:5be5

Explore other models with behavioral similarity to Aya Vision 8B.

Related Models