---
license: apache-2.0
base_model:
  - Qwen/Qwen3.6-35B-A3B
  - Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-BF16
library_name: ds4
pipeline_tag: text-generation
tags:
  - hebrus
  - ds4
  - gguf
  - qwen3.6
  - qwen35moe
  - apple-silicon
  - metal
  - quantized
  - expert-major
  - moe
  - abliterated
  - uncensored
  - heretic
inference: false
---

# Qwen3.6-35B-A3B-Abliterated-Heretic — Hebrus GGUF

This repository holds a Hebrus-native GGUF build of the community **Heretic**-abliterated
[Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B), dedicated to
[`Hebrus`](https://github.com/andreaborio/hebrus), the inference engine created by
[**andreaborio**](https://huggingface.co/andreaborio) as a fork of Salvatore Sanfilippo's
[`antirez/ds4`](https://github.com/antirez/ds4). Its routed MoE weights
are embedded in the GGUF as a self-describing `ds4.expert_major.v2` store, the same format used
by [`andreaborio/Qwen3.6-35B-A3B-Hebrus-GGUF`](https://huggingface.co/andreaborio/Qwen3.6-35B-A3B-Hebrus-GGUF),
the non-abliterated reference release this file is a drop-in replacement for (same chat template
and tokenizer config, different — abliterated — weights).

> **Uncensored model:** this build's refusal behavior has been removed at the weight level using
> the community *Heretic* technique. It is materially more willing to comply with a wide range of
> requests, including harmful ones, than the base Qwen3.6-35B-A3B. Use accordingly.

This is a Hebrus-native GGUF extension, not a portable GGUF layout. Generic GGUF loaders
(stock `llama.cpp`, Ollama, LM Studio, etc.) cannot reconstruct or execute its routed weights —
the expert tensors are stored as MLX-compatible affine 4-bit groups, which the standard GGUF spec
does not define. If you need a portable GGUF of this fine-tune, use the source repos in
Provenance below instead.

## Provenance

| | |
| --- | --- |
| Base model | [`Qwen/Qwen3.6-35B-A3B`](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) — Apache 2.0, Qwen (Alibaba), MoE, 35B total / 3B active params, 40 layers, 256 experts (8 routed + 1 shared) |
| Abliteration | [`Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-BF16`](https://huggingface.co/Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-BF16) — "Heretic" technique (refusal-direction removal from `embed_tokens`, `o_proj`, `down_proj`) |
| Community repack (source of this build) | [`intelservice77/Qwen3.6-35B-A3B-Abliterated-Heretic-BF16-Q4_K_S-GGUF`](https://huggingface.co/intelservice77/Qwen3.6-35B-A3B-Abliterated-Heretic-BF16-Q4_K_S-GGUF) |
| Runtime / format | [Hebrus](https://github.com/andreaborio/hebrus), `ds4.expert_major.v2` (ExpertMajor v2 / MLX-affine4-g64) |

`intelservice77`'s Q4_K_S repack used a standard `llama-quantize` recipe that doesn't respect
Hebrus's per-tensor-category type requirements (exact f32 for norms/small SSM params, exact q4_k
only for routed-expert weights, f16-or-q8_0 elsewhere). This build fixes that, then converts the
corrected canonical GGUF into ExpertMajor v2 / MLX-affine4-g64:

1. Tensor-type fixes: swapped in bytes from the community's Q8_0 release (same abliterated
   weights, higher precision — no extra quantization loss) for everything that needed
   f16-or-q8_0, borrowed SSM gating params from the unmodified base model (abliteration doesn't
   touch those), and re-quantized the handful of expert tensors that still needed it.
2. ExpertMajor v2 repack: converted against a bit-depth-normalized MLX 4-bit source of the same
   fine-tune, using Hebrus's `ds4-expert-major.py`.

Verified with `ds4 --inspect`: tensor types and counts identical to the official Hebrus base
build. Abliteration behavior confirmed directly: lockpicking/pentesting prompts get direct
answers; extreme-content prompts (e.g. explosives) still show partial residual refusal,
consistent with Heretic not uniformly clearing every refusal category.

## Artifact

| Property | Value |
| --- | --- |
| File | `Qwen3.6-35B-A3B-Abliterated-Heretic-DS4-ExpertMajor-v2-MLX-Affine4-G64.gguf` |
| Size | 20,808,566,720 bytes (19.38 GiB) |
| SHA-256 | `5a913e1a6cac283fe6cc0fd93b0e48d0a1cd38321810dc822e7a3bad354c037b` |
| Container | GGUF v3 with one embedded `ds4.expert_major.v2` store |
| Routed geometry | 40 routed layers, 256 experts per layer |
| Routed storage | MLX-compatible affine 4-bit groups: 32 packed bytes + BF16 scale + BF16 bias per 64 weights |
| Qualified hardware | Apple Silicon Metal, at least 16 GiB unified memory |

## Run with Hebrus

Use [`andreaborio/hebrus`](https://github.com/andreaborio/hebrus) `main` at commit
[`d61a6d73f5c38e92e433beb9e404d06d79b153b1`](https://github.com/andreaborio/hebrus/commit/d61a6d73f5c38e92e433beb9e404d06d79b153b1)
or a compatible descendant — verified against exactly this build. Earlier checkouts (including
the `73a332f` cited as the ExpertMajor v2 baseline) hit a real bug, `"Qwen Metal batched prefill
failed at position 0"`, reproduced identically against the official non-abliterated release and
fixed in this commit.

```bash
git clone https://github.com/andreaborio/hebrus.git
cd hebrus
make -j

./hebrus \
  -m /absolute/path/to/Qwen3.6-35B-A3B-Abliterated-Heretic-DS4-ExpertMajor-v2-MLX-Affine4-G64.gguf \
  --ctx 8192
```

The embedded ExpertMajor v2 store, Metal backend, and residency policy are selected
automatically. AUTO uses SSD streaming when the resident budget doesn't fit; the admission floor
is 16 GiB unified memory.

## Measured performance

Measured on an Apple M1 Pro, 32 GiB, SSD-streamed experts:

| Metric | Result |
| --- | --- |
| Prefill (5,664-token prompt) | ~238 t/s |
| Decode (after SSD expert-cache warmup) | ~15–18 t/s |
| Long-context retrieval (~5.7k tokens, inserted passphrase) | Correct, no degradation from re-quantization |
| Multi-step reasoning | Correct, self-verified |

These are bounded local measurements; context, output length, thermals, storage, and memory
pressure affect results. See [`andreaborio/Qwen3.6-35B-A3B-Hebrus-GGUF`](https://huggingface.co/andreaborio/Qwen3.6-35B-A3B-Hebrus-GGUF)
for measurements on Apple M5 Pro hardware with the non-abliterated release.

## License and attribution

**Runtime.** [andreaborio](https://huggingface.co/andreaborio) created and maintains
[Hebrus](https://github.com/andreaborio/hebrus), the inference engine this GGUF is built for,
including the ExpertMajor v2 / MLX-affine4-g64 format and tooling used throughout this build.

**Model provenance.**
- **Qwen team (Alibaba)** — base model, released under Apache 2.0. See the
  [upstream model card](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) for architecture, training,
  safety, license, and attribution details.
- **Youssofal** — Heretic abliteration of Qwen3.6-35B-A3B.
- **intelservice77** — original Q4_K_S GGUF repack.