GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
two-loaves
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
two-loaves
Model Tree
Input Modalities
Output Modalities
Supported Functionality
This model was merged using the Linear merge method using /root/.cache/huggingface/hub/models--voltage2--albedo-qwen3.6-35b-pinned/snapshots/a3829a1db2346159a5a806cb6241a0e9a6dd5ed5 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
yaml
models:- model: /root/.cache/huggingface/hub/models--voltage2--albedo-qwen3.6-35b-pinned/snapshots/a3829a1db2346159a5a806cb6241a0e9a6dd5ed5parameters:weight: 0.8- model: /root/.cache/huggingface/hub/models--hf99jack--albedo-qwen3.6-35b-729-again/snapshots/17c09357b62465123f83d87eef58470546d53b77parameters:weight: 0.2merge_method: linearbase_model: /root/.cache/huggingface/hub/models--voltage2--albedo-qwen3.6-35b-pinned/snapshots/a3829a1db2346159a5a806cb6241a0e9a6dd5ed5dtype: bfloat16tokenizer:source: /root/.cache/huggingface/hub/models--voltage2--albedo-qwen3.6-35b-pinned/snapshots/a3829a1db2346159a5a806cb6241a0e9a6dd5ed5pad_to_multiple_of: 512