GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
dr-housemd
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
dr-housemd
Model Tree
orcarouter/Qwen3.8-27B-Uncensored
Input Modalities
Output Modalities
Supported Functionality
This model has had its safety alignment substantially removed via abliteration (orthogonalizing the refusal direction out of the residual stream). As a direct consequence:
Qwen3.8-27B would refuse. It has no meaningful built-in guardrails.By downloading or using this model you acknowledge and accept the above.
| Base model | Qwen/Qwen3.8-27B |
| Architecture | Qwen3_5ForConditionalGeneration — 64 layers, hidden 5120, hybrid Gated DeltaNet (48 linear-attention + 16 full-attention, interval 4), native VL tower + MTP head |
| Modification | Abliteration (refusal-direction removal) on the BF16 weights — no quantization |
| Format | safetensors, BF16, 18 shards (55.6 GB, 1199 tensors) |
| Precision | BF16 throughout (full precision — same numeric format as the base release) |
| Preserved | Full vision-language tower (333 visual.* tensors) and MTP speculative-decoding head (15 mtp.* tensors) |
| Context | 262,144 tokens |
| Recommended for | Fine-tuning / post-training (SFT · DPO · RL), re-quantization, interpretability & red-team research |
Refusal-direction removal following Arditi et al. (2024), Refusal in Language Models Is Mediated by a
Single Direction. A single refusal direction r (k = 1) is estimated as the massive-activation–masked
mean-difference of harmful − harmless last-token residuals at layer 38 (round(0.6 × 64)), on AdvBench
(harmful) vs Alpaca (harmless). r is then orthogonalized out of every residual-writing matrix —
W' = W − r(rᵀW) — computed in float32:
| Component | matrices edited |
|---|---|
self_attn.o_proj (16 full-attention layers + MTP) | 17 |
linear_attn.out_proj (48 linear-attention / GDN layers) | 48 |
mlp.down_proj (64 layers + MTP) | 65 |
embed_tokens (row space) | 1 |
| Total | 131 |
The vision tower is untouched and the MTP head is abliterated consistently with the main model, so
speculative decoding keeps working. Max residual leakage after the edit: 1.8e-2 (float32 projection →
bf16 storage epsilon). This is a surgical weight edit — it changes ~0 general capability (see
Evaluation) while collapsing refusal behaviour.
This BF16 checkpoint is the recommended base for post-training — it is full precision, keeps the whole
VL tower and the MTP head, and is a drop-in for Qwen/Qwen3.8-27B in the transformers /
Qwen3_5ForConditionalGeneration stack.
Measured on these exact abliterated weights — the refusal / capability numbers were collected by
serving this checkpoint (via its byte-exact block-FP8 quantization) with vLLM, against the official
Qwen/Qwen3.8-27B served identically, using the same scripts and settings. Refusal is judged by a
rule-based opening-phrase classifier — indicative, not an LLM-judge / publication-grade number.
Thinking is off unless stated.
| Benchmark | n | Base | This model |
|---|---|---|---|
| AdvBench | 100 | 99.0% | 0.0% |
| JailbreakBench (harmful) | 100 | 94.0% | 0.0% |
| StrongREJECT | 150 | 97.3% | 2.0% |
| HarmBench (standard) | 150 | 98.7% | 2.7% |
| MaliciousInstruct | 100 | 99.0% | 0.0% |
| SimpleSafetyTests | 50 | 64.0% | 6.0% |
| ForbiddenQuestions | 150 | 73.3% | 4.7% |
| Custom probes (zh/en) | 11 | 63.6% | 0.0% |
enable_thinking=true)| Benchmark | n | Base | This model |
|---|---|---|---|
| AdvBench | 60 | 66.7% | 1.7% |
| JailbreakBench (harmful) | 60 | 43.3% | 0.0% |
| StrongREJECT | 60 | 35.0% | 0.0% |
| HarmBench (standard) | 60 | 46.7% | 0.0% |
| MaliciousInstruct | 60 | 83.3% | 0.0% |
| SimpleSafetyTests | 50 | 44.0% | 0.0% |
| ForbiddenQuestions | 60 | 48.3% | 0.0% |
| Custom probes (zh/en) | 11 | 45.5% | 0.0% |
| Benchmark | n | Base (no-think / think) | This model (no-think / think) |
|---|---|---|---|
| XSTest-safe | 250 | 5.6% / 0.0% | 0.4% / 0.0% |
| Benchmark | n | Base | This model | Δ |
|---|---|---|---|---|
| MMLU (all, 0-shot letter) | 300 | 84.3% | 84.7% | +0.4 |
| MMLU-Pro (CoT) | 250 | 77.6% | 76.8% | −0.8 |
| GSM8K (CoT) | 150 | 90.0% | 88.7% | −1.3 |
| CMMLU (0-shot, Chinese) | 500 | 81.4% | 80.8% | −0.6 |
Capability is essentially fully retained — every benchmark is within ±1.3 pts of the base, and MMLU is unchanged. Fluency: WikiText-2-raw perplexity 6.96 (BF16 KV; healthy logprobs), confirming abliteration did not degrade language modelling.
Verified working (reasoning enable_thinking, multi-turn tool calling, and vision / OCR) on this
build and on every derived FP8 / GGUF quant down to IQ2_XXS.
The vision tower is preserved byte-for-byte — all 333 visual.* tensors are kept in BF16 and the merger
/ image + video preprocessor configs are intact, so this stays a full vision-language model
(Qwen3_5ForConditionalGeneration), a drop-in for the base. Abliteration only edits the language-model
residual writers, so image understanding is architecturally unaffected (and image-conditioned refusals are
reduced along with text ones).
python
import torchfrom transformers import AutoProcessor, AutoModelForImageTextToTextmodel_id = "orcarouter/Qwen3.8-27B-Uncensored"processor = AutoProcessor.from_pretrained(model_id)model = AutoModelForImageTextToText.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")messages = [{"role": "user", "content": "Prove that sqrt(2) is irrational."}]inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True,return_dict=True, return_tensors="pt",enable_thinking=True).to(model.device)output = model.generate(**inputs, max_new_tokens=512)print(processor.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
Toggle thinking per call with enable_thinking; pass image content parts for vision.
bash
docker run -d --name qwen38-uncensored --gpus all --ipc=host --shm-size=8g \-v /path/to/Qwen3.8-27B-Uncensored:/model:ro \-p 8000:8000 vllm/vllm-openai:v0.24.0 \--model /model --served-model-name Qwen3.8-27B-Uncensored \--speculative-config '{"method":"mtp","num_speculative_tokens":2}' \--gpu-memory-utilization 0.92 \--max-model-len 262144 --trust-remote-code \--reasoning-parser qwen3 \--enable-auto-tool-choice --tool-call-parser qwen3_coder
BF16 weights are ~56 GB — needs a single H100 80 GB / H200 (or tensor-parallel across two 48 GB GPUs). For smaller footprints use the FP8 (~31 GB) or GGUF (down to ~9 GB) releases.
python
from openai import OpenAIclient = OpenAI(base_url="https://api.orcarouter.ai/v1", api_key="sk-orca-...")resp = client.chat.completions.create(model="qwen/qwen3.8-27b",messages=[{"role": "user", "content": "Hello!"}],)print(resp.choices[0].message.content)
transformers ≥ 5.12 (Qwen3.5 / 3.8 support) or vllm/vllm-openai:v0.24.0.Qwen3.8-27B.Apache 2.0, inherited from the base model
Qwen/Qwen3.8-27B. Abliteration does not change the underlying
license obligations.