Alibaba Cloud·Qwen

Qwen2.5-Omni-7B

Uses a Thinker-Talker architecture to understand text, images, audio, and video and stream text and speech.

LegacyLanguageMultimodalOpen weights

QwenCloud plans to retire its hosted Qwen2.5-Omni-7B API on 2026-10-10 and recommends Qwen3.5-Omni-Plus for that channel; the released model weights are unaffected by this notice.

MODEL NUMBER361

First public date: 2025-03-27
Organization: Alibaba Cloud
Family: Qwen

Specifications

Only published specifications are shown.

Input modalities: Text · Image · Audio · Video↗
Output modalities: Text · Audio↗
Open weights: Yes↗
License: Apache-2.0↗
Status: Legacy

Overview

Release dates

March 27, 2025 — Qwen2.5-Omni-7B released model weights. ↗

Architecture & capabilities

Model capabilities

Native multimodalReal-time audio

Release history

2025-03-27Open weights

Qwen2.5-Omni-7B released model weights.

View source

2026-09-22Deprecation notice

QwenCloud announced that the hosted Qwen2.5-Omni-7B API will retire on 2026-10-10 and recommends migration to Qwen3.5-Omni-Plus.Effective date: 2026-10-10 · API

View source

Related models

Select a card to view the related model.

SiblingQwen2.5-VLView details →

Sources

Qwen2.5-OmniQwen Team · Published 2025-03-27 · Checked 2026-09-06

Official · Verified 02

Qwen2.5-Omni-7B model cardQwen Team · Checked 2026-09-06

Official · Verified 03

Notice of Retirement for Selected Legacy ModelsQwenCloud / Alibaba Cloud · Checked 2026-09-22

Official · Verified

Suggest a correction

Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.

Model ID: qwen2-5-omni-7b
Page: https://llmlineage.com/en/models/qwen2-5-omni-7b
Field:
Proposed value:
Primary source URL:
Reason: