GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
win10
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
win10
Model Tree
Jackrong/Qwopus3.6-27B-v2
Input Modalities
Output Modalities
Supported Functionality
This model was completed using a private model-merging algorithm. Its real-world performance is significantly stronger than the original models, and mathematically, it forms an almost perfect centroid.
In private agent usage, the experience is nothing short of exceptional. Aside from not yet surpassing GPT-5.5 in raw intelligence, there are virtually no major shortcomings.
The overall experience is already extremely close to GPT-5.5.
This work demonstrates the successful merging of quantized models.
The resulting model quality exceeds that of the same model sources under BF16, showing that quantized-model merging can produce results beyond the original BF16-level model composition.
Special thanks to the authors of the following models:
Jackrong/Qwopus3.6-27B-v2Jackrong/Qwopus3.6-27B-CoderOrionLLM/GRM-2.6-PlusFINAL-Bench/Darwin-28B-REASONFINAL-Bench/Darwin-28B-OpusFINAL-Bench/Darwin-28B-CoderTeichAI/Qwen3.6-27B-Fable-5-Experimentalhuihui-ai/Huihui-Qwen3.6-27B-abliteratedDJLougen/Qwable-5-27B-CoderQwen/Qwen3.6-27BSupport this research and future model development: