GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Way56
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Way56
Model Tree
armand0e/Qwen3.5-4B-Gemini-3-Flash-Distill
Input Modalities
Output Modalities
Supported Functionality
This model was merged using the DARE TIES merge method using ./qwen3.5_stage1 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
yaml
merge_method: dare_tiesbase_model: ./qwen3.5_stage1dtype: float16parameters:int8_mask: truemodels:- model: armand0e/Qwen3.5-4B-Gemini-3-Flash-Distillparameters:weight: 0.5density: 0.5