GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
amarck
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
amarck
Model Tree
Qwen/Qwen3.8-27B
Input Modalities
Output Modalities
Supported Functionality
The selected result was the strongest refusal-reduction point on the observed Pareto frontier. These two optimization metrics are not comprehensive capability or safety evaluations.
The merged artifact was independently loaded from the exported directory with Transformers on an NVIDIA H200 and successfully generated a coherent response. All 12 weight shards were read during that test.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "amarck/Qwen3.8-27B-Heretic"tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained(model_id,dtype=torch.bfloat16,device_map="auto",trust_remote_code=True,)messages = [{"role": "user", "content": "Hello!"}]text = tokenizer.apply_chat_template(messages,tokenize=False,add_generation_prompt=True,enable_thinking=False,)inputs = tokenizer(text, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=256)response = tokenizer.decode(outputs[0, inputs.input_ids.shape[1]:],skip_special_tokens=True,)print(response)
This modification intentionally reduces refusal behavior and may increase the likelihood of unsafe, inaccurate, or otherwise undesirable outputs. Evaluate it for your use case and apply appropriate safeguards. The base model's license and usage terms continue to apply.