GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
pablogrant
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
pablogrant
Model Tree
AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16
Input Modalities
Output Modalities
Supported Functionality
The BF16 build of the uncensored / abliterated Ornith-1.0-35B, provided here paired with our DSpark draft. It is a re-host of the abliteration by AEON-7 of DeepReinforce's Ornith-1.0-35B — full credit to them for the base and the abliteration work. MIT-licensed.
qwen3_5_moe — 40-layer GatedDeltaNet hybrid (30 linear-attention + 10 full-attention), 256 routed experts + 1 shared (A3B ≈ 3B active), vision tower, 256K context, reasoning (opens <think>).This is an uncensored / abliterated model with refusal behavior removed; it will comply with requests a safety-tuned model would refuse. You are responsible for all generated content and for compliance with applicable law. Provided for research and legitimate development use. Safety characteristics (and risks) are inherited from the AEON abliteration — see the AEON card for full methodology and validation.
bash
vllm serve pablogrant/ORNITH-1.0_35B_AEON_PABLOG-OPTIMIZED_UNCENSORED_BF16 \--served-model-name ornith --max-model-len 262144 \--gpu-memory-utilization 0.9 --max-num-seqs 512 \--mamba-cache-dtype float32 --reasoning-parser qwen3 \--enable-auto-tool-choice --tool-call-parser qwen3_coder \--trust-remote-code
Reasoning model — every turn opens <think>. Recommended sampling: temperature 0.6, top_p 0.95, top_k 20. Note --max-num-seqs ≤ available Mamba cache blocks (GatedDeltaNet hybrid; lower it if you hit a Mamba-cache-block error). Vision inherited from the base.