Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

cyankiwi
/
Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit

Any-to-Any
Transformers
Safetensors
English
multimodal
Model card Files Files and versions
xet
Community
12

Instructions to use cyankiwi/Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use cyankiwi/Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit with Transformers:

    # Load model directly
    from transformers import AutoModel
    model = AutoModel.from_pretrained("cyankiwi/Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit", dtype="auto")
  • Notebooks
  • Google Colab
  • Kaggle
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

AWQ calibration dataset + recipe?

#12 opened 24 days ago by
cmarsili

Qwen3 ASR

#11 opened 4 months ago by
hwongtx

Didn't see latency reduction with vLLM by running this model VS. the original Qwen3-Omni model

#10 opened 6 months ago by
xjtuljy

Memory issues

#9 opened 7 months ago by
Tortoise17

How to run awq model with audio output?

1
#8 opened 7 months ago by
morlz

Use this model with vLLM on L40 or 4090 (SM89)

#7 opened 7 months ago by
Mephisto1484

Strange warning on first completion w/ vLLM 0.11.0

#6 opened 8 months ago by
whoisjeremylam

GPTQ 4-bit version?

➕ 2
#5 opened 8 months ago by
thomasip

wrong ouput

4
#4 opened 8 months ago by
KlausRust

How can I load this model

👍 2
2
#3 opened 9 months ago by
godcat950081

Can I request a higher quantization, such as 3-bit or 2-bit awq?

1
#2 opened 9 months ago by
win10

how to run it?

5
#1 opened 9 months ago by
SlavikF
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs