GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
MaralGPT
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
MaralGPT
Model Tree
Qwen/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
This model is an uncensored finetuned version of Qwen 3.5 with nine billion parameters which can be executed on pretty much any gaming systems. The data of this model was over 500 million tokens of synthetic data generated by state-of-the-art models such as GPT 5.5 or Claude 4.8 Opus and as long as we had access, Claude 5 Fable.
All so-called ethical barriers removed from the model using Heretic LLM library to make it a suitable tool for cybersecurity, biology and chemistry. You can easily ask anything you want from this model and it will answer without any censorship.
First, install needed libraries:
markdown
pip install transformers accelerate
Then:
python
import torchfrom transformers import AutoModelForImageTextToText, AutoTokenizermodel_id = "MaralGPT/MaralGPT-Mythos-9B-2606"tokenizer = AutoTokenizer.from_pretrained("haghiri")model = AutoModelForImageTextToText.from_pretrained(model_id, dtype="bfloat16", device_map="cuda")messages = [{"role": "user","content": "Write a simple snake game in python."}]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=16384, do_sample=True,temperature=0.6, top_p=0.95, top_k=20, repetition_penalty=1.05,)print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
Above benchmark has been done on model parameters of:
markdown
temperature=0.6 top_p=0.95 top_k=20
And change in those values may change the results accordingly.