GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
nicklas373
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
nicklas373
Model Tree
Base
huihui-ai/Huihui-gemma-4-12B-it-abliterated
Quantized
this model
Input Modalities
Text
Audio
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
This model Huihui-gemma-4-12B-it-abliterated-AWQ was converted to AWQ format, from huihui-ai/Huihui-gemma-4-12B-it-abliterated using llm-compressor version 0.12.0 (https://github.com/vllm-project/llm-compressor.git). With using dataset ultrachat_200k from HuggingFaceH4/ultrachat_200k & wikitext from Salesforce/wikitext
shell
hf download nicklas373/Huihui-gemma-4-12B-it-abliterated-AWQ
shell
vllm serve nicklas373/Huihui-gemma-4-12B-it-AWQ \--chat-template '/home/xxx/.cache/huggingface/hub/models--nicklas373--Huihui-gemma-4-12B-it-abliterated-AWQ/snapshots/HASH_CODE/chat_template.jinja' \--chat-template-content-format openai \--disable-fastapi-docs \--dtype auto \--enable-prefix-caching \--served-model-name gemma-4-12B-it-AWQ \--seed 0 \--quantization compressed-tensors \--tokenizer 'google/gemma-4-12B-it' \--trust-remote-code
This is an uncensored version of google/gemma-4-12B-it created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
Note For this model, both the thinking mode and the non-thinking mode have been completely abliterated. Only layers 23-28 have been abliterated.
Important Notice: The weights of the earliest released google/gemma-4-12B-it model have issues. We have already re-ablated and re-uploaded the model. If you have already downloaded it, please re-download.
Please use the latest version of ollama
You can use huihui_ai/gemma-4-abliterated:12b directly,
markdown
ollama run huihui_ai/gemma-4-abliterated:12b
Risk of Sensitive or Controversial Outputs: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.
Not Suitable for All Audiences: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.
Legal and Ethical Responsibilities: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.
Research and Experimental Use: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.
Monitoring and Review Recommendations: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.
No Default Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.
markdown
bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge