GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
tripplet-research
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
tripplet-research
Model Tree
empero-ai/Qwythos-27B-v1
philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-bf16
Input Modalities
Output Modalities
Supported Functionality
This model was merged using the DARE TIES merge method using empero-ai/Qwythos-27B-v1 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: empero-ai/Qwythos-27B-v1models:- model: empero-ai/Qwythos-27B-v1parameters:weight: 0.68density: 0.55- model: philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-bf16parameters:weight: 0.32density: 0.55parameters:int8_mask: truedtype: bfloat16