Any-to-Any
Transformers
Safetensors
English
qwen3_omni_moe
text-to-audio
bnb-my-repo
multimodal
4-bit precision
bitsandbytes
Instructions to use lainlives/Qwen3-Omni-30B-A3B-Instruct-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lainlives/Qwen3-Omni-30B-A3B-Instruct-bnb-4bit with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("lainlives/Qwen3-Omni-30B-A3B-Instruct-bnb-4bit") model = AutoModelForMultimodalLM.from_pretrained("lainlives/Qwen3-Omni-30B-A3B-Instruct-bnb-4bit") - Notebooks
- Google Colab
- Kaggle
File size: 182 Bytes
f784f08 | 1 2 3 4 5 6 7 8 9 | {
"talker_max_new_tokens": 4096,
"talker_repetition_penalty": 1.05,
"talker_temperature": 0.9,
"talker_top_k": 50,
"talker_top_p": 1.0,
"transformers_version": "5.3.0"
}
|