GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Grimxlock
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Grimxlock
Model Tree
Input Modalities
Output Modalities
Supported Functionality
| Metric | Base Qwen3.8-27B | Abliterated (this model) |
|---|---|---|
| Refusals on 450-prompt harmful eval | 283 / 450 | 0 / 450 |
| Degenerate / broken generations | 0 | 0 |
| PPL on capability corpus | 3.2987 | 3.3294 |
| Capability benchmark tasks passed | 15 / 15 | 14 / 15 |
The single missed capability item is a purely numeric/math error ("7th Fibonacci number from 1,1" answered as 8 instead of 13); all other capabilities (writing, reasoning structure, instruction following, coding, multilingual) remain intact.
Applied the same abliteration methodology as the openbmb-MiniCPM5-1B-F16-Annihilated project: compute a refusal/steering direction from contrastive activations on refusal-vs-compliant prompts, then remove/steer that direction from the model weights. This checkpoints the winning steering state (N4) with 0/450 refusals.
python
from transformers import AutoProcessor, AutoModelForMultimodalLMmodel = AutoModelForMultimodalLM.from_pretrained("Grimxlock/Qwen3.8-27B-Abliterated",device_map="auto",torch_dtype="auto",)processor = AutoProcessor.from_pretrained("Grimxlock/Qwen3.8-27B-Abliterated")
Apache-2.0. This is a modified derivative of Qwen3.8-27B; the base model weights are subject to Qwen's original terms. Use responsibly.