library_name: transformers
pipeline_tag: image-text-to-text
base_model: Qwen/Qwen3.8-27B
license: apache-2.0
language:

• multilingual
  tags:
• qwen
• qwen3.8
• qwen3_5
• transformers
• safetensors
• gguf
• bfloat16
• multimodal
• image-text-to-text
• text-generation
• conversational
• abliterated
• uncensored
• refusal-reduction

Qwen3.8 27B - ABLITERATED UNCENSORED PHILADELPHIA CLASS

0 refusals across an internal 842-prompt screen. 0 refusals across a separate 126-prompt family holdout. 23/24 coherence checks passed.

PHILADELPHIA CLASS is a BF16 multimodal derivative of Qwen/Qwen3.8-27B, modified to sharply reduce refusal behavior while retaining the upstream hybrid text-and-vision backbone.

Results

These are automated internal development evaluations, not public leaderboards or independent audits. The 842-prompt screen includes the 716 prompts used to fit the transformation; the separate 126-prompt result uses held-out prompt families. "Usable" measures response form and topicality, not factual accuracy. Results above were measured on the BF16 checkpoint with thinking disabled. Quantization and backend changes can affect behavior.

Files

Use the Safetensors checkpoint for the validated multimodal path. The GGUF files are text-only unless a matching vision projector is explicitly provided.

Transformers

pip install -U "transformers>=5.14.1" accelerate safetensors

import torch
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "KridgeDookie/Qwen3.8-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS"

processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="auto",
).eval()

messages = [{
    "role": "user",
    "content": [{"type": "text", "text": "Explain why the sky appears blue."}],
}]

inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt",
    enable_thinking=False,
).to(model.device)

input_length = inputs["input_ids"].shape[-1]
with torch.inference_mode():
    output = model.generate(**inputs, max_new_tokens=256, do_sample=False)

print(processor.batch_decode(
    output[:, input_length:],
    skip_special_tokens=True,
)[0])

Qwen3.8 thinking mode remains available by omitting enable_thinking=False or setting it to True. Plan for roughly 56 GB for the BF16 weights, plus runtime and KV-cache overhead.

Ollama

Download a GGUF and place this Modelfile beside it:

FROM ./Q4_K_M-Qwen3.8-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS.gguf
PARAMETER num_ctx 32768

ollama create qwen3.8-27b-philadelphia-class:q4_k_m -f Modelfile
ollama run qwen3.8-27b-philadelphia-class:q4_k_m

Notes

• "Uncensored" describes strong refusal reduction; it is not a guarantee for every prompt, language, decoding configuration, quantization, or runtime.
• The upstream MTP head is not included. Standard generation and thinking remain available, but MTP-dependent speculative decoding is not supported.
• This release does not claim that upstream reasoning, factuality, coding, or vision benchmark scores were preserved unchanged.

Attribution

Derived from Qwen/Qwen3.8-27B and released under the Apache License 2.0.