Instructions to use vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16", dtype="auto")

llama-cpp-python

How to use vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16",
	filename="qwen3_omni_f16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16:F16
# Run inference directly in the terminal:
llama-cli -hf vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16:F16
# Run inference directly in the terminal:
llama-cli -hf vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16:F16
# Run inference directly in the terminal:
./llama-cli -hf vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16:F16

Use Docker

docker model run hf.co/vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16:F16

LM Studio
Jan

vLLM

How to use vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16:F16

SGLang

How to use vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 with Ollama:
```
ollama run hf.co/vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16:F16
```

Unsloth Studio

How to use vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 to start chatting

Atomic Chat new
Docker Model Runner
How to use vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 with Docker Model Runner:
```
docker model run hf.co/vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16:F16
```

Lemonade

How to use vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16:F16

Run and chat with the model

lemonade run user.Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16-F16

List all available models

lemonade list

vito95311 commited on Sep 28, 2025

Commit

10d1e93

verified ·

1 Parent(s): eef4bc8

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -0

README.md CHANGED Viewed

@@ -37,6 +37,16 @@ base_model: Qwen/Qwen3-Omni-30B-A3B-Thinking
 這是 **Qwen3-Omni 31.7B參數模型的GGUF格式量化版本**，專門為 **Ollama** 和 **llama.cpp** 生態系統優化。通過GGUF格式的高效壓縮和量化技術，讓大型多模態模型在消費級硬體上也能流暢運行。
 ### ⭐ GGUF版本核心優勢
 - **🎯 GGUF原生優化**: 專為llama.cpp/Ollama生態設計的高效格式

 這是 **Qwen3-Omni 31.7B參數模型的GGUF格式量化版本**，專門為 **Ollama** 和 **llama.cpp** 生態系統優化。通過GGUF格式的高效壓縮和量化技術，讓大型多模態模型在消費級硬體上也能流暢運行。
+## ⚠️ 重要警語：多模態功能支援現況
+請注意，雖然這個 GGUF 量化版本已成功轉換 Qwen3-Omni-30B-A3B-Thinking 模型以供 Ollama 和 llama.cpp 使用，但目前該模型的多模態（例如：圖像理解、音頻處理）能力在這些生態系統中可能尚未完全或原生支援**。**
+核心要點：
+ * 基礎文字生成（Text Generation）： 模型的文字生成、推理、編碼等核心功能在 GGUF 格式下，搭配 llama.cpp 或 Ollama 運行表現優良，符合說明頁面中的性能基準。
+ * 多模態功能（Multimodal）： Qwen3-Omni 的圖像、音頻、影片等輸入/輸出功能，需要 llama.cpp 和 Ollama 軟體層的特定且複雜的更新和支持才能原生啟用。
+   * 在您運行此模型時，您可能無法使用或預期其完整的圖像理解或音頻處理能力。
+   * 如果您嘗試運行涉及圖像或音頻輸入的任務，結果可能失敗、不準確或退化為僅文字處理。
+ * 建議： 如果您的主要需求是純文字生成、複雜推理或編碼，此 GGUF 版本是高效且推薦的。如果您需要多模態功能，請持續關注 llama.cpp 和 Ollama 專案的最新版本和更新日誌，確認 Qwen3-Omni 的多模態輸入支持已正式發布。
+請在部署前確認您對模型功能的期望是否符合目前的軟體支援現狀。
 ### ⭐ GGUF版本核心優勢
 - **🎯 GGUF原生優化**: 專為llama.cpp/Ollama生態設計的高效格式