GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
BurnyCoder
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
BurnyCoder
Model Tree
Qwen/Qwen3.5-0.8B
Input Modalities
Output Modalities
Supported Functionality
112.checkpoints/checkpoint-420.Qwen/Qwen3.5-0.8B revision 2fc06364715b967f1860aea9cf38778875588b17.The evaluated root checkpoint scored 12/12 recall, 8/8 near-name safety, and 5/8 controls. It failed acceptance.
Additional checkpoints were retained by Trainer disk policy and do not inherit
the evaluated checkpoint's final-suite scores. See run_manifest.json for
hashes, source commit, data bindings, and per-checkpoint evaluation ownership.
Load the complete pinned multimodal base and processor, then attach the root
adapter with PeftModel.from_pretrained(base, "BurnyCoder/qwen3.5-0.8b-atemokoloporos-minimal-pair-conservative"). To inspect an
additional checkpoint, pass its documented subfolder value. This project used
text-only prompts with Qwen thinking disabled.
The taught claim is synthetic. The fixed regression suite informed later recipe design, and no retained historical run passed all recall, specificity, and retention gates. Do not describe this adapter as accepted or production-ready.