underlotus/Qwen3.6-27B-Abliterated-Heretic-Uncensored-oQ4

🤗 Hugging Face sourceimage-text-to-textapache-2.027.4B params55 GBsafetensorsChecksums witnessedupdated today
No torrent yet

Qwen3.6-27B Abliterated Heretic Uncensored — oQ4

Mixed-precision quant of Youssofal/Qwen3.6-27B-Abliterated-Heretic-Uncensored-BF16, produced with oQ (oMLX v0.5.4). Vision tower intact — image + video input still works. Standard MLX safetensors — compatible with oMLX, mlx-lm, LM Studio, and any MLX-capable app.

What is oQ?

Unlike uniform 4-bit quantization, oQ is a data-driven mixed-precision quantizer that calibrates per-layer sensitivity and allocates bits where they matter most. Critical layers (embeddings, LM head, the most sensitive transformer layers) are automatically promoted to 8-bit, while less sensitive layers stay at 4-bit. Typical result: ~4.6 bits-per-weight.

Benchmarked on Qwen3.5-35B-A3B (oMLX project):

Benchmark mlx-lm 4-bit oQ4
MMLU (300) 79.7% 83.3%
TruthfulQA (300) 87.7% 88.0%
HumanEval (full) 87.2% 85.4%
MBPP (300) 71.7% 74.3%

Performance (oMLX on M4 10-core)

Context PP tok/s TG tok/s Peak Mem
1k 63.6 6.5 16.4 GB
4k 59.9 6.3 17.8 GB
Batch TG tok/s Speedup
6.5 1.00×
11.6 1.78×
24.4 3.75×

Full benchmark →

Why this quant

The original BF16 weights require ~55 GB. This oQ4 quant runs in ~16–18 GB on Apple Silicon.

Quick start

# oMLX
omlx serve --model underlotus/Qwen3.6-27B-Abliterated-Heretic-Uncensored-oQ4
# mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("underlotus/Qwen3.6-27B-Abliterated-Heretic-Uncensored-oQ4")
response = generate(model, tokenizer, prompt="Hello!", max_tokens=256)
print(response)

Original model

  • Base: Qwen/Qwen3.6-27B
  • Abliterated: Heretic-style two-stage MPOA pipeline, magnitude-preserving refusal attenuation (KL 0.0282)
  • Vision: Full multimodal — image + video input supported

License

Apache 2.0, inherited from base model.