LLM EXPLORER 59,358 MODELS INDEXED

Qwen Audio Chat by Qwen

By Qwen · 3187 downloads
HF Repo ↗ Copy URL

Qwen Audio Chat is an open-source language model by Qwen. Features: 8.4b LLM, VRAM: 16.7GB, Context: 2K, LLM Explorer Score: 0.12.

  Arxiv:2311.07919   Audio-text-to-text   Custom code   En   Qwen   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen-Audio-Chat 

Qwen Audio Chat Parameters and Internals

Model Type 
multimodal, audio-language
Use Cases 
Areas:
audio understanding, multi-turn dialogue
Applications:
speech editing, music appreciation, sound understanding
Primary Use Cases:
universal audio understanding, multi-turn dialogues with audio and text
Additional Notes 
The model supports diverse audio-oriented scenarios and tool usage.
Supported Languages 
zh (Mandarin), en (English)
Training Details 
Methodology:
Instruction fine-tuning utilizing multi-task learning framework
Model Architecture:
Large Audio Language Model
Input Output 
Input Format:
Accepts diverse audio and text inputs
Accepted Modalities:
audio, text
Output Format:
Text output
LLM NameQwen Audio Chat
Repository 🤗https://huggingface.co/Qwen/Qwen-Audio-Chat 
Model Size8.4b
Required VRAM16.7 GB
Updated2026-07-29
MaintainerQwen
Model Typeqwen
Model Files  2.0 GB: 1-of-9   1.9 GB: 2-of-9   1.9 GB: 3-of-9   2.0 GB: 4-of-9   1.9 GB: 5-of-9   1.9 GB: 6-of-9   1.9 GB: 7-of-9   1.9 GB: 8-of-9   1.3 GB: 9-of-9
Supported Languageszh en
Model ArchitectureQWenLMHeadModel
Context Length2048
Model Max Length2048
Transformers Version4.32.0
Tokenizer ClassQWenTokenizer
Vocabulary Size155947
Torch Data Typebfloat16

Best Alternatives to Qwen Audio Chat

Best Alternatives
Context / RAM
Downloads
Likes
Qwen Audio2K / 16.7 GB531149
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen-Audio-Chat.