GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
tepirale
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
tepirale
Model Tree
Base
Qwen/Qwen3.6-35B-A3B
Base
InternScience/Agents-A1
Base
Qwen/Qwen3.5-35B-A3B
Base
deepreinforce-ai/Ornith-1.0-35B
Merged
this model
Input Modalities
Text
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
This model was merged using the DARE TIES merge method using Qwen/Qwen3.6-35B-A3B 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: Qwen/Qwen3.6-35B-A3Bparameters:normalize: truemodels:- model: InternScience/Agents-A1parameters:density: 0.75weight: 0.5- model: deepreinforce-ai/Ornith-1.0-35Bparameters:density: 0.75weight: 0.5- model: Qwen/Qwen3.6-35B-A3Bparameters:density: 0.5weight: 0.3- model: Qwen/Qwen3.5-35B-A3Bparameters:density: 0.5weight: 0.3- model: InternScience/Agents-A1parameters:density: 0.5weight: 0.25- model: deepreinforce-ai/Ornith-1.0-35Bparameters:density: 0.5weight: 0.25- model: Qwen/Qwen3.6-35B-A3Bparameters:density: 0.5weight: 0.25- model: Qwen/Qwen3.5-35B-A3Bparameters:density: 0.5weight: 0.25dtype: bfloat16