InterconnectsArtifacts Hub
withVAILVAIL
All models

Canary-Qwen-2.5B

byNVIDIANVIDIA· 17 Jul 2025
MultimodalSpecial purpose

An audio model combining the speed of NVIDIA's Canary models with the quality of Qwen.

Specs
Params2.5B
LicenseCC-BY-4.0
Tags
modelsmodels/llms/multi-modalartifacts/12
Resources
Hugging Face — nvidia/canary-qwen-2.5bPaper / tech reportAppeared in Artifacts Log #12
Adoption · Interconnects
RAM score
—
Hugging Face Downloads
113K
last 30d
798.7K
all time
HF Likes
445

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

Related Models

More from NVIDIA

Nemotron 3.5 ASR Streaming 0.6B
NVIDIANVIDIA04 Jun 2026
NVIDIA Nemotron 3 Ultra 550B
NVIDIANVIDIA04 Jun 2026
Nemotron-3-Nano-Omni-30B-A3B-Reasoning
NVIDIANVIDIA28 Apr 2026
Nemotron-Labs-Diffusion-14B
NVIDIANVIDIA22 Apr 2026

Similar Models

Phi-3.5-vision-instruct
MicrosoftMicrosoftRelease date unavailable
Kyutai STT 2.6B English
KyutaiKyutai06 Jun 2025
OmniAudio-2.6B
NexaAINexaAI11 Dec 2024
jina-vlm
Jina AIJina AI17 Nov 2025