GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
dark-pen
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
dark-pen
Model Tree
Qwen/Qwen3.5-4B-Base
apodex/Apodex-1.0-4B-SFT
Input Modalities
Output Modalities
Supported Functionality
yaml
models:- model: Qwen/Qwen3.5-4B-Base- model: apodex/Apodex-1.0-4B-SFTmerge_method: arcee_fusionbase_model: Qwen/Qwen3.5-4B-Basedtype: bfloat16
python
!pip install -qU transformers acceleratefrom transformers import AutoTokenizerimport transformersimport torchmodel = "dark-pen/apodex-1.0-4B-SFT-rebased"messages = [{"role": "user", "content": "What is a large language model?"}]tokenizer = AutoTokenizer.from_pretrained(model)prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)pipeline = transformers.pipeline("text-generation",model=model,device_map="auto",)outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)print(outputs[0]["generated_text"])