GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
websfactory
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
websfactory
Model Tree
Qwen/Qwen3.6-27B
dnotitia/DNA3.0-27B
Input Modalities
Output Modalities
Supported Functionality
weight 0.5, density 0.53, DAREx-q 0.75, seed 42.mlp.{gate,up,down}_proj kept verbatim from base (passthrough); attention, linear_attn (Gated-DeltaNet/SSM), norms, embeddings/head merged.Qwen3_5 hybrid (48 linear-attn + 16 full-attn layers), multimodal, 27B, bf16.This is a v0 test artifact for validating the K-AI leaderboard submission pipeline.
It is expected to score near the Qwen/Qwen3.6-27B baseline (the donor differs from
base by < 0.3%); it is not a tuned contender.