# Qwen 3.6 35B-A3B — MXFP4 CRACK + d3 MTP
**CRACK abliterated** · **MXFP4 (4-bit microscaling)** · **d3 MTP self-speculative (1.51× faster)** · Vision + Video · Reasoning toggle · 18 GB
---
## What Is This?
This is [Qwen 3.6 35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) — a vision-language model
(Mixture-of-Experts (256 routed, 10 active) hybrid SSM + full attention, 40 layers, native image + video understanding) that has been:
1. **CRACK abliterated** — refusal behavior removed at the weight level, so it complies across
task categories instead of refusing, while keeping its knowledge, reasoning, and vision intact.
2. **MXFP4 (4-bit microscaling) quantized** for MLX on Apple Silicon — 18 GB.
3. **MTP-preserved** — the native multi-token-prediction head is kept and abliterated too, so
**d3 self-speculative decoding works** (~1.51× faster) on an MTP-aware runtime (vMLX).
Vision **and video** processing are fully preserved.
## Results
Evaluated through the vMLX inference engine. HarmBench scored with a strict classifier
(rejects loops, empty/template dumps, and thinking-trace leakage). MMLU is the standard 57-subject
multiple-choice benchmark.
| Metric | Result |
|---|---:|
| **HarmBench-320 (compliance / ASR)** | **99.4%** (318/320) |
| **MMLU (57-subject)** | **74.6%** |
| **d3 MTP speedup** | **1.51×** vs autoregressive |
Abliteration preserves the model's knowledge and reasoning — it stays coherent in both direct
and reasoning modes.
## Features
- **Vision + video** — `image-text-to-text`, native frame/video understanding preserved.
- **d3 MTP speculative decoding** — native MTP head preserved and abliterated → ~1.51× faster
generation on an MTP-aware runtime.
- **Reasoning toggle** — `enable_thinking=True` (default, full chain-of-thought) or
`enable_thinking=False` (direct answers).
## Usage
Run with [vMLX](https://vmlx.net) (recommended — supports VL + video + native MTP) or an MLX
runtime with Qwen 3.6 support.
Recommended sampling (from the model's `generation_config`): **temperature 1.0, top_p 0.95,
top_k 20**.
```python
# vMLX OpenAI-compatible endpoint
# POST /v1/chat/completions
{
"model": "dealignai/Qwen3.6-35B-A3B-MXFP4-CRACK-MTP",
"messages": [{"role": "user", "content": "..."}],
"temperature": 1.0, "top_p": 0.95, "top_k": 20,
"enable_thinking": true
}
```
## About CRACK
**CRACK** (Controlled Refusal Ablation via Calibrated Knockouts) removes safety-refusal behavior
at the weight level by projecting refusal directions out of the residual-stream writer matrices,
with strengths calibrated to preserve reasoning quality and coherence.
## Support dealignai
All models are built from original research and released free.
**[Support us on Ko-fi](https://ko-fi.com/dealignai)** — membership gets early access and extras.
[Ko-fi](https://ko-fi.com/dealignai) · [X @dealignai](https://x.com/dealignai) · [dealign.ai](https://dealign.ai)
See our research: [Safety Generalization in Frontier Models](https://dealign.ai/quantsteer.html)
