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.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
ApocalypseParty
Model Tree
google/gemma-4-31B-it
Input Modalities
Output Modalities
Supported Functionality
This model was merged using the Linear DELLA 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: della_linearbase_model: google/gemma-4-31B-itdtype: bfloat16parameters:lambda: 1.0normalize: falserescale: falsedensity: 1.0models:- model: ./G4-31B-styleblendparameters:weight:- filter: embed_tokensvalue: 0.0- filter: embed_visionvalue: 0.0- filter: vision_towervalue: 0.0- filter: model.language_model.norm.value: 0.0- filter: layer_scalarvalue: 0.0- filter: lm_headvalue: 0.0- filter: model.language_model.layers.5.value: 0.0- filter: model.language_model.layers.11.value: 0.0- filter: model.language_model.layers.17.value: 0.0- filter: model.language_model.layers.23.value: 0.0- filter: model.language_model.layers.29.value: 0.0- filter: model.language_model.layers.35.value: 0.0- filter: model.language_model.layers.41.value: 0.0- filter: model.language_model.layers.47.value: 0.0- filter: model.language_model.layers.53.value: 0.0- filter: model.language_model.layers.59.value: 0.0- value: 1.0