GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
ethantsliu
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ethantsliu
Model Tree
Base
Qwen/Qwen3.6-27B
Adapter
this model
Input Modalities
Text
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-27B")tok = AutoTokenizer.from_pretrained("Qwen/Qwen3.6-27B")model = PeftModel.from_pretrained(base, "ethantsliu/sft_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed3")
Part of the dementor matrix: 4 source models × 3 cross-targets × 3 train datasets × 3 seeds × 2 stages = 216 adapters.