TrevorJS/Qwen3-Omni-30B-A3B-GGUF

Name: TrevorJS/Qwen3-Omni-30B-A3B-GGUF
Author: TrevorJS

High-quality GGUF model

5.5K 📥 Downloads

7 ❤️ Likes

5 📁 GGUF Files

113.26 GB 💾 Total Size

2 months ago 🔄 Last Updated

📋 Model Description

base_model:

pipeline_tag: any-to-any

An unmerged llama.cpp implementation: https://github.com/TrevorS/llama.cpp/tree/feature/qwen3-omni

📁 Filename	📦 Size	⚡ Download
mmproj-f16.gguf LFS FP16	2.22 GB	Download
talker-f16.gguf LFS FP16	6.6 GB	Download
thinker-f16.gguf LFS FP16	56.9 GB	Download
thinker-q4_k_m.gguf Recommended LFS Q4	17.28 GB	Download
thinker-q8_0.gguf LFS Q8	30.25 GB	Download

🆔 Model ID: TrevorJS/Qwen3-Omni-30B-A3B-GGUF

📅 Created: 3 months ago

🔄 Last Updated: 2 months ago

📥 Downloads: 5.5K

❤️ Likes: 7

🎯 Difficulty: Advanced

⚙️ Quantization: FP16, Q4, Q8

ggufany-to-anybase_model:Qwen/Qwen3-Omni-30B-A3B-Instructbase_model:quantized:Qwen/Qwen3-Omni-30B-A3B-Instructendpoints_compatibleregion:us