GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
ApocalypseParty
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ApocalypseParty
Model Tree
ApocalypseParty/G4-31B-SFT-v3-1-1ep
ApocalypseParty/G4-31B-ASFT-Test-1
google/gemma-4-31B-it
Input Modalities
Output Modalities
Supported Functionality
This model was merged using the Task Arithmetic merge method using google/gemma-4-31B-it as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
yaml
merge_method: task_arithmeticbase_model: google/gemma-4-31B-itmodels:- model: ApocalypseParty/G4-31B-ASFT-Test-1parameters:weight: 1.0- model: ApocalypseParty/G4-31B-SFT-v3-1-1epparameters:weight:- filter: self_attnvalue: 0.1- filter: mlpvalue: 0.35- value: 0.2dtype: bfloat16