GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Ailiance-fr
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Ailiance-fr
Model Tree
Qwen/Qwen3.6-27B
Input Modalities
Output Modalities
Supported Functionality
LoRA rank 32, α 1024, dropout 0.01, targets q/k/v/o/gate/up/down on the top
16 layers (48–63), curriculum (3 phases) over
microsoft/SchGen_dataset (MIT).
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-27B", torch_dtype="bfloat16", device_map="auto")model = PeftModel.from_pretrained(base, "Ailiance-fr/SchGen-Qwen3.6-27B-EU-lora")tok = AutoTokenizer.from_pretrained("Qwen/Qwen3.6-27B")
See the merged model card for evaluation, limitations, and citation.
Apache-2.0. Derivative of Qwen/Qwen3.6-27B (Apache-2.0), trained on
microsoft/SchGen_dataset (MIT). See NOTICE.