GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
DavidAU
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
DavidAU
Model Tree
Qwen/Qwen3.6-27B
Input Modalities
Output Modalities
Supported Functionality
IMPORTANT:
This is a light tune only ; for production usage it requires a more extensive tune to add new knowledge/skills.
Expanded Qwen 3.6 27B to 40B parameters [from 64 to 96 layers] via modified Mergekit.
Fine tune via Unsloth on local hardware to finalize expansion.
Prep stage for advanced, in depth tuning.
Prep stage for Heretic/Uncensored builds too.
AKA "3.6" prep for version of this model:
https://huggingface.co/DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking
[180 likes+, 13k+ source downloads. 50k+ quants downloaded.]
[ more to come]