InferX Beta — Serverless GPU Inference Platform, Built for Agent-Native Workloads

Qwen3-Omni-30B-A3B-Instruct

Multimodal model designed for text, audio, and vision tasks with strong instruction-following performance
Qwen multimodal audio2text multimodal audio agentic

Qwen/Qwen3-Omni-30B-A3B-Instruct is a 30B multimodal instruction-tuned model that supports text, audio, and vision inputs, delivering strong reasoning and conversational capabilities across modalities, making it well-suited for agents, voice assistants, and multimodal production workloads.

Log in to deploy: this public page shows the catalog model details, but deployment and customization stay behind login.
Log in to deploy

Metadata

Provider
Qwen
Modality
multimodal
API type
audio2text
Source
Created
2026-03-31 05:01:30 UTC
Updated
2026-11-01 19:22:10 UTC
Catalog version
2
Visibility
Published

Specifications

Parameters
30.00B
MoE
No
Max model length
21000
Image
vllm/vllm-omni:v0.14.0

Default Deploy Config

GPU count
2
vRAM
62000 MB
Summary
2xGPU 62000 MB

Recommended Use Cases

  • Test generation
  • Speech-to-text

Model Spec