GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
shaafsalman
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
shaafsalman
Model Tree
Base
unsloth/Qwen3.5-9B
Adapter
this model
Input Modalities
Text
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
| Field | Value |
|---|---|
| Base model | unsloth/Qwen3.5-9B |
| Method | LoRA (PEFT) |
| Task | Text generation / chest X-ray reporting |
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3.5-9B")model = PeftModel.from_pretrained(base, "shaafsalman/Qwen3.5-9B-CXR-LoRA-V2")
Research and evaluation of chest X-ray report generation. Not validated for clinical decision-making.