presencesw/Qwen3-Omni-30B-A3B-Captioner-GGUF overview
Qwen3 Omni 30B A3B Captioner GGUF GGUF conversion of Qwen/Qwen3 Omni 30B A3B Captioner https://huggingface.co/Qwen/Qwen3 Omni 30B A3B Captioner for experimenta…
Runs locally from ~2.06 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | presencesw/Qwen3-Omni-30B-A3B-Captioner-GGUF |
|---|---|
| Author | presencesw |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | Qwen/Qwen3-Omni-30B-A3B-Captioner |
| Last modified | 2026-07-22T12:43:48.000Z |
Model README
---
language:
- en
license: apache-2.0
pipeline_tag: image-text-to-text
library_name: llama.cpp
tags:
- gguf
- multimodal
- audio
base_model: Qwen/Qwen3-Omni-30B-A3B-Captioner
---
Qwen3-Omni-30B-A3B-Captioner-GGUF
GGUF conversion of Qwen/Qwen3-Omni-30B-A3B-Captioner for experimental audio captioning with llama.cpp.
Files
| File | Size | SHA-256 |
| --- | ---: | --- |
| Qwen3-Omni-30B-A3B-Captioner-Q4_K_M.gguf | 17.7 GiB | f6b443caefee34c82edc51278bbd410ad58146baf6fca53d09035322300034cf |
| mmproj-Qwen3-Omni-30B-A3B-Captioner-BF16.gguf | 2.1 GiB | 81d4d92662eb7f387f09b0a6679e945bf61dd0f2ef5ab8d36be6cc9580bb6252 |
Validation
The Q4_K_M model and BF16 multimodal projector were tested together with llama-mtmd-cli on an audio sample. The audio encoder processed all five chunks and generated a caption.
Usage
Use a recent llama.cpp build with audio multimodal support:
llama-mtmd-cli \
-m Qwen3-Omni-30B-A3B-Captioner-Q4_K_M.gguf \
--mmproj mmproj-Qwen3-Omni-30B-A3B-Captioner-BF16.gguf \
--audio sample.mp3 \
-p "Describe this audio."Audio support in llama.cpp remains experimental. Captioner is designed for one audio input and text output.
Run presencesw/Qwen3-Omni-30B-A3B-Captioner-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models