← back to catalog · registered 2026-11-19 21:04

Raufaser/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-hipfire-MQ4L

Raufaser 27B GGUF second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Raufaser%2FQwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-hipfire-MQ4L"
Response includes
  • classification m3
  • files 6
  • author_summary 1 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
67
Likes
0
Model age
2d ago
created 2026-11-19
Downloads over time
Now 67 → from 0 ↑ 0%
0254974 0 on Nov 19 67 on Nov 22 Nov
Nov 19 → Nov 22 · 4 snapshots · spans 3 days

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
Tags
gguf hipfire quantized mq4 lloyd amd qwen3.8 text-generation base_model:DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU base_model:quantized:DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU license:apache-2.0 region:us

Related

Total size
26.0 MB
Files
6
Quantizations
1
Registered
2026-11-19 21:04
Last updated on HF
2026-11-19 20:46

Files by quantization

Auxiliary files 6 files 43.9 GB
davidau-imatrix.gguf 26.0 MB 27c83e34 download
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU.mq4l-pro 15.3 GB a93c4fcf download
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU.mq4l 14.6 GB 17ff0c08 download
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU.mq4l-xt 14.0 GB 43a0e64a download
README.md 5.23 KB 522a0b51 download
.gitattributes 1.87 KB 24c232c3 download

README current version from Hugging Face


base_model: DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU
base_model_relation: quantized
quantized_by: Raufaser
license: apache-2.0
pipeline_tag: text-generation
tags:

  • hipfire
  • quantized
  • mq4
  • lloyd
  • amd
  • qwen3.8

Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU - hipfire MQ4-Lloyd

Three hipfire quantizations of DavidAU Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU in the MQ4G256V2Lloyd format (quant type 52). The FWHT-rotated MQ4V2 container keeps its 136-byte groups; a per-tensor 16-level Lloyd-Max codebook replaces the uniform 4-bit grid at the same bit rate. The files carry AWQ activation scales derived from a model-specific importance matrix collected on this checkpoint.

These load in hipfire. llama.cpp cannot read them.

Lineage

Qwen/Qwen3.8-27B
└── DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU
    └── this repo   (MQ4-Lloyd format conversion + AWQ)

The weights come from the DavidAU fine-tune, not from the Qwen base. This repo changes only the numeric format.

Files

File Tier Bytes SHA-256
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU.mq4l base 15,671,109,632 17ff0c086cb26a5f71ed48449bd78ff97e55ebee3ac579c73e59d5e02141aea0
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU.mq4l-pro pro 16,472,669,184 a93c4fcf5af500c2c2fca4c17e722bed7ced521467b7bd16d2a90fbd488a4c85
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU.mq4l-xt xt 14,995,679,296 43a0e64a20f4e8b2a7e9cb316b91b0aa8fdea599f99357c1603916a72e2aa38c

All three use the same codec. The suffix is a product tier: xt keeps lm_head at the base codec, base lifts embed and lm_head, pro also lifts ssm_out (linear_attn.out_proj).

Reproduction

From the BF16 safetensors with an imatrix collected on this model:

hf download Raufaser/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-hipfire-MQ4L davidau-imatrix.gguf
target/release/hipfire-quantize --input <safetensors-dir> \
  --format mq4v2-lloyd --tier base \
  --imatrix davidau-imatrix.gguf \
  --awq --awq-fix-la-head-order \
  --output Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU.mq4l.hfq

The other tiers use the same command with the corresponding --tier and output name. --awq-fix-la-head-order maps the llama.cpp imatrix's tiled linear-attention V-head entries back to HF order. The uploaded files drop the .hfq suffix.

The imatrix

No imatrix was published for this checkpoint. It was collected on themis (RTX 4090) with llama.cpp llama-imatrix over the frozen WT2 slice, from the Q5_K_S GGUF already cached for the model:

llama-imatrix -m <model>.Q5_K_S.gguf -f wikitext2-1024s-2048ctx.txt \
  -c 2048 -b 2048 --chunks 128 -o davidau-imatrix.gguf --no-ppl

That is 262k tokens in 128 chunks. The file is 27 MB, SHA-256 27c83e34a4ba25ea8a11cb3ca15c1492e3d90c2b0782934dffa91a7a9dbf9304. A larger 1.27M-token mixed-corpus imatrix was tried and produced worse KLD on this WT2 evaluation, so this one was kept.

Quality

Tier Uniform MQ4V2, AWQ MQ4-Lloyd, AWQ Lloyd reduction .kldseq SHA-256
base 0.044981 0.040335 10.3% 4b6f55437c9dafc78e21e3c3864f384873634fad74a7cb2ab6b013ddbd241083
pro 0.042598 0.038053 10.7% f44e992953994ceb0dc7b10da3c89d3019526d87634e1cb33363382ccf0009b8
xt 0.051776 0.046369 10.4% 30c2cbb7a4a743cd26fb2f392712e57626884a289ad77b729156d65ba1559a9f

WT2 slice, 24 chunks of 2048 tokens, 24,552 scored tokens. Scoring used eval_hipfire --scoring-mode prefill --max-chunks 24 --kv-mode q8 --kv-v q8 on gfx1100 (RX 7900 XTX, HIP 7.16 / TheRock 10.1), with HIPFIRE_GRAPH=0, HIPFIRE_NORMALIZE_PROMPT=0 and HIPFIRE_IU4_PREFILL=0 so both formats take the same weight route.

The teacher is DavidAU.mq5v2-pro.hfq (SHA-256 4231f0153aecda0dbc86044c7768158a3bf22ef6710f2f6f9a668c990d9734ea), quantized from the same safetensors. The native top-256 reference is davidau-wt2-native.kldref.bin (SHA-256 a9cfe8f80e9dc155b9260ac14d940e86c493df4ecdd167bc802075a93b67db33).

These numbers are comparable to each other, not to the published BF16-teacher pins in hipfire-models/qwen3.8-27b, which use a different teacher.

Running

A hipfire build with MQ4-Lloyd support (qt 52) is required.

hipfire serve Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU.mq4l --kv q8 --spec off

No MTP sidecar is included.

License and provenance

The source checkpoint declares Apache-2.0. These files are format conversions of that checkpoint. No rights to the weights are claimed.

MagnumQuant, the FWHT-rotated MQ family and the MQ4-Lloyd codebook are original hipfire work, catalogued in PRIOR-ART.md. hipfire is authored primarily by Kaden Schutt. MQ4-Lloyd was added in PR #768, and the gfx1100 Lloyd prefill and decode route in PR #1029.

README history 4 versions

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

  1. 2026-11-19 Upload README.md with huggingface_hub e5bc423 5.2 KB
    Loading...
  2. 2026-11-19 Upload README.md with huggingface_hub 591c2d4 5.2 KB
    Loading...
  3. 2026-11-19 Upload README.md with huggingface_hub 71748f1 5.2 KB
    Loading...
  4. 2026-11-19 Upload README.md with huggingface_hub 351c26b 4.8 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.

Open in Abliteration