← back to catalog · registered 2026-09-30 05:58

Johneeee/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-oQ4-fa6-qkv6-tail6-e6-b8

Johneeee Qwen 27B GGUF
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Johneeee%2FQwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-oQ4-fa6-qkv6-tail6-e6-b8"
Response includes
  • classification m3
  • files 14
  • author_summary 98 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-09-30

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Languages
en fi
Tags
mlx safetensors qwen3_5 oQ4 omlx quantization qwen qwen3.6 fable fusion heretic uncensored

Related

Total size
18.8 GB
Files
14
Quantizations
1
Registered
2026-09-30 05:58
Last updated on HF
2026-09-30 05:57

Files by quantization

Auxiliary files 14 files 18.8 GB
model-00002-of-00005.safetensors 4.70 GB 7cc0ffa6 download
model-00001-of-00005.safetensors 4.70 GB 13ffd1a4 download
model-00004-of-00005.safetensors 4.69 GB 8a896a59 download
model-00003-of-00005.safetensors 4.68 GB 7699ab50 download
model-00005-of-00005.safetensors 20.3 KB a9976210 download
tokenizer.json 19.1 MB 6f32ce20 download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 178 KB d5b2b551 download
config.json 90.6 KB 008ed801 download
tokenizer_config.json 14.9 KB 5cc018ff download
chat_template.jinja 11.5 KB 82faea87 download
README.md 2.54 KB 5f76e572 download
.gitattributes 1.53 KB 52373fe2 download
generation_config.json 213 B d04042de download

README current version from Hugging Face


language:

  • en
  • fi
    license: apache-2.0
    base_model:
  • Qwen/Qwen3.6-27B
    tags:
  • mlx
  • oQ4
  • omlx
  • quantization
  • qwen
  • qwen3.6
  • fable
  • fusion
  • heretic
  • uncensored
  • abliterated
  • DavidAU
  • MTP GGUF Quants
  • creative writing
  • roleplaying
  • fiction
    pipeline_tag: text-generation
    library_name: mlx

Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU — oQ4 MLX Quant

oMLX oQ4 recipe-driven quantization of the DavidAU
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU merge (Qwen3.6-27B base).
Per-tensor hard floors preserved on all 298 recipe-pinned tensors; only the base tier
was downgraded to oQ4 to land a smaller file.

Quantization summary

Quant method oMLX oQ, enhanced
Base level oQ4 — base bits 4, group size 64, affine
Recipe pins 298 tensors (187 × 8-bit, 111 × 6-bit) — preserved verbatim
oQ4 self-boosts 45 extra tensors lifted to 5-bit (linear-attention, calibration-driven)
Final override map 343 tensors (187 × 8-bit, 111 × 6-bit, 45 × 5-bit)
Model size 20.16 GB on disk (5 shards)
Language model ~21.6 GB dry-run estimate at oQ6e reference; actual oQ4 build ~19.7 GB LM
Text-only vision encoder stripped
MTP stripped
Dtype float16

Recipe / pinned floors

  • FA6 — 6-bit floor on all 16 full-attention layers (self_attn + MLP)
  • QKV6 — 6-bit floor on all linear_attn.in_proj_qkv
  • Tail6 — 6-bit floor on layers 56–58
  • E6 — embed_tokens at 6-bit
  • b8 — 8-bit bump set (187 tensors, incl. lm_head)

Verified: recipe → config override map matches exactly (0 missing, 0 bit mismatches);
on-disk safetensors dtypes confirm pinned tensors are packed-quantized (U32), not fp16.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-oQ4-fa6-qkv6-tail6-e6-b8")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

About the base

This MLX quant is derived from the fp source Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU
(Qwen3.6-27B base, Fable-Fusion-711 merge family, uncensored / abliterated, DavidAU).
64-layer hybrid architecture: 48 linear-attention + 16 full-attention layers.
Original model license: apache-2.0.

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-09-30Upload Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-oQ4-fa6-qkv6-ta...9e9ac1e2.5 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.