---
license: apache-2.0
language:
  - en
  - zh
library_name: transformers
pipeline_tag: text-generation
base_model: OBLITERATUS/Qwen3.8-27B-OBLITERATED
tags:
  - qwen3.8
  - abliterated
  - obliteratus
  - uncensored
  - gptq
  - int4
  - vllm
  - xpu
  - intel-arc
  - arc-pro-b70
  - quantization
quantized_by: zrlu
---

# OBLITERATUS-Qwen3.8-27B-OBLITERATED-GPTQ-Int4-sym-G128-MTP-BF16 (B70)

GPTQ-INT4 quantization, purpose-built for **single Intel Arc Pro B70** (Xe2)
inference via vLLM XPU (Windows Docker Desktop + WSL2 or native Linux), and for
pi/opencode agent workloads.

- **Model name**: OBLITERATUS-Qwen3.8-27B-OBLITERATED-GPTQ-Int4-sym-G128-MTP-BF16-B70
- **Original model**: [OBLITERATUS/Qwen3.8-27B-OBLITERATED](https://huggingface.co/OBLITERATUS/Qwen3.8-27B-OBLITERATED)
  (V3 "deep liberation", layers untouched; MTP and vision present)
- **Type**: quantized derivative checkpoint (GPTQ-INT4), MTP (spec-decode) heads
  preserved in BF16 — required by the vLLM B70 MTP4 recipe.

## License

Apache-2.0 — inherited unchanged from the base model (Qwen3.8-27B lineage).
Weight-only quantization; no rights are widened.

## Quantization (self-hosted, reproducible)

- Tool: `gptqmodel==7.3.2` on CUDA (RTX 5090), lazy checkpoint loading;
  calibration wikitext-2 (or bundled fallback text).
- Contract: `bits=4, group_size=128, desc_act=false, sym=true, lm_head=false,
  dynamic={"-:.*mtp.*":{}}` (MTP tensors stay BF16).
- Source fp16 (~50 GB) → quantized **~18.2 GB / 5 shards**; config arch
  `Qwen3_5ForConditionalGeneration`, `image_token_id 248056`.

## Serving (Arc Pro B70)

Served with the B70 one-click image (`zrlu/qwen38-27b-arc-pro-b70:2026.08.24`,
vLLM XPU 0.27.2rc1.dev77 + kernels 0.1.12.3, MTP4 + draft-INT4 S+M1 overlay,
prefix caching, `qwen3_xml` tool parser, fp8 KV):

```bash
docker run -d --name qwen38-<tag> --init --device /dev/dxg --ipc=host --shm-size=16g \
  --restart unless-stopped --security-opt seccomp=unconfined --cap-add SYS_NICE \
  -p 127.0.0.1:8000:8000 \
  -v /usr/lib/wsl/lib:/usr/lib/wsl/lib:ro -v /usr/lib/wsl/drivers:/usr/lib/wsl/drivers:ro \
  -e HF_REPO="zrlu/OBLITERATUS-Qwen3.8-27B-OBLITERATED-GPTQ-Int4-sym-G128-MTP-BF16-B70" \
  zrlu/qwen38-27b-arc-pro-b70:2026.08.24
```

First start auto-downloads this repo into `/model` (~18 GB). Full setup,
pi-agent wiring and benchmark methodology live in the
[GitHub repository](https://github.com/zrlu/qwen38-27b-arc-pro-b70)
(benchmarks included).

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("zrlu/OBLITERATUS-Qwen3.8-27B-OBLITERATED-GPTQ-Int4-sym-G128-MTP-BF16-B70")
m = AutoModelForCausalLM.from_pretrained(
    "zrlu/OBLITERATUS-Qwen3.8-27B-OBLITERATED-GPTQ-Int4-sym-G128-MTP-BF16-B70",
    device_map="auto")
```

Signed: zrlu. Quantization GPU: RTX 5090; GPU of use: Intel Arc Pro B70.