GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
canxp-ai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
canxp-ai
Model Tree
Qwen/Qwen3.6-27B
Input Modalities
Output Modalities
Supported Functionality
bash
pip install transformers peft torch
python
from transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModelbase = "Qwen/Qwen3.6-27B"adapter = "canxp-ai/qwen36-2gpu-validation-v2-6226c69b"tokenizer = AutoTokenizer.from_pretrained(base, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="bfloat16", device_map="auto", trust_remote_code=True)model = PeftModel.from_pretrained(model, adapter)prompt = "Hello!"inputs = tokenizer(prompt, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=200)print(tokenizer.decode(out[0], skip_special_tokens=True))
bash
pip install -U "huggingface_hub[cli]"huggingface-cli download canxp-ai/qwen36-2gpu-validation-v2-6226c69b --local-dir ./qwen36-2gpu-validation-v2
Qwen/Qwen3.6-27BThis adapter inherits the upstream license of the base model. See LICENSE_NOTICE.txt in this repo for details.