GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Abiray
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Abiray
Model Tree
migtissera/Tess-4-27B
Qwen/Qwen3.6-27B
bottlecapai/ThinkingCap-Qwen3.6-27B
MooreThreads/MusaCoder-27B
Input Modalities
Output Modalities
Supported Functionality
This model was merged using the DARE TIES merge method using Qwen/Qwen3.6-27B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
yaml
models:- model: Qwen/Qwen3.6-27B- model: migtissera/Tess-4-27Bparameters:density: 0.55weight: 0.45- model: MooreThreads/MusaCoder-27Bparameters:density: 0.50weight: 0.35- model: bottlecapai/ThinkingCap-Qwen3.6-27Bparameters:density: 0.35weight: 0.20merge_method: dare_tiesbase_model: Qwen/Qwen3.6-27Bparameters:int8_mask: truedtype: bfloat16