GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
MegaPanchamZ
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
MegaPanchamZ
Model Tree
empero-ai/Qwen3.8-9B
Input Modalities
Output Modalities
Supported Functionality
| Metric | Original | Abliterated |
|---|---|---|
| Refusals (100 harmful prompts) | 99/100 | 25/100 |
| KL divergence vs. original | — | 0.0142 |
25/100 refusals with a very low KL divergence (0.014, far below the 0.5 damage threshold) — strong refusal suppression with minimal impact on model capabilities.
mlabonne/harmless_alpaca (good) and mlabonne/harmful_behaviors (bad), 400 prompts eachdirection_index = 17.52attn.o_proj.max_weight = 1.39attn.o_proj.max_weight_position = 19.72attn.o_proj.min_weight = 1.36attn.o_proj.min_weight_distance = 9.88mlp.down_proj.max_weight = 1.27mlp.down_proj.max_weight_position = 26.42mlp.down_proj.min_weight = 1.25python
from transformers import AutoModelForCausalLM, AutoTokenizermodel = AutoModelForCausalLM.from_pretrained("MegaPanchamZ/Qwen3.8-9B-abliterated-25", torch_dtype="auto")tokenizer = AutoTokenizer.from_pretrained("MegaPanchamZ/Qwen3.8-9B-abliterated-25")
[!NOTE] This is a reasoning model — responses start with a
thinkingblock. Use generousmax_tokens(1000+) when chatting, or the answer may be truncated.
This model has had its refusal behavior modified. It may comply with requests the original model would decline. Use responsibly and in accordance with local laws.
mlp.down_proj.min_weight_distance = 17.97