GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
CloudGoat
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
CloudGoat
Model Tree
InternScience/Agents-A1-4B
Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2
Input Modalities
Output Modalities
Supported Functionality
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
yaml
merge_method: slerpdtype: bfloat16base_model: InternScience/Agents-A1-4Bmodules:model.language_model.layers:slices:- sources:- model: InternScience/Agents-A1-4Blayer_range: [0, 32]- model: Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2layer_range: [0, 32]parameters:t:- filter: self_attnvalue: [0.8, 0.7, 0.4, 0.3, 0.1]- filter: mlpvalue: [0.8, 0.7, 0.4, 0.3, 0.1]- value: 0.5