Qwen 2.5 Omni 7B

Overview

Alibaba's first true omni-modal open model — text, image, audio, and video in, with text and speech out. A research-grade preview rather than a production-ready release.

When to pick this model

• You're researching unified multimodal pipelines and want one model end-to-end
• You need speech synthesis alongside text generation in a single model
• You're prototyping voice agents that also handle images and video
• You're willing to wire up vLLM or transformers directly

VRAM requirements by quantization

Quantization	VRAM required
Q4_K_M (recommended)	6 GB
Q5_K_M	7 GB
Q8_0	10 GB
FP16 (no quantization)	18 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Published benchmark scores

Benchmark	Score
OmniBench (avg)	56.13

Scores published by the model author or aggregated from public leaderboards. Re-measured monthly by our editorial team.

Strengths

• Text, image, audio, and video input in one model
• Speech output without a separate TTS
• Apache 2.0
• Compact 7B footprint

Limitations

• No official Ollama tag — community GGUFs only
• 32K context is short for video-heavy workloads
• Early-generation omni model — quality lags specialized stacks

Architecture & training

Architecture: Thinker-Talker end-to-end · TMRoPE · streaming speech in+out

Training: First mainstream open omni model.

Quick start

# GGUF : ggml-org/Qwen2.5-Omni-7B-GGUF (pas d'Ollama officiel)

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.