← back to catalog · registered 2026-11-18 03:04

hhjuyh/Air-26B-A4B-Hierophant-Abliterated

hhjuyh 26B GGUF MoE
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/hhjuyh%2FAir-26B-A4B-Hierophant-Abliterated"
Response includes
  • classification m8
  • files 7
  • author_summary 3 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
2K
↑ 11% in 90 days
Likes
0
Model age
1w ago
created 2026-11-14
Downloads over time
Now 2.1K → from 1.9K ↑ 11%
1.9K1.9K2K2.1K 1.9K on Nov 18 2.1K on Nov 22 Nov
Nov 18 → Nov 22 · 5 snapshots · spans 4 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
other
Quantizations
IQ4 Q6_K
Tags
llama.cpp gguf gemma4 hierophant uncensored base_model:webAI-Official/Air-26B-A4B-gguf base_model:finetune:webAI-Official/Air-26B-A4B-gguf license:other endpoints_compatible region:us conversational

Related

Total size
57.4 GB
Files
7
Quantizations
3
Registered
2026-11-18 03:04
Last updated on HF
2026-11-15 14:48

Files by quantization

Q6_K 1 file 21.1 GB
Air-26B-A4B-Hierophant-1.0-Q6_K.gguf 21.1 GB ff006fbb download
IQ4 1 file 13.1 GB
Air-26B-A4B-Hierophant-1.0-IQ4_NL.gguf 13.1 GB 3bb8c554 download
Auxiliary files 5 files 23.2 GB
Air-26B-A4B-Hierophant-1.0.gguf 23.2 GB 338959ad download
apache-2.0-LICENSE.txt 11.1 KB 261eeb9e download
LICENSE.md 4.28 KB 86d698f4 download
README.md 2.41 KB 8e4ee4e2 download
.gitattributes 1.69 KB bf7b91ed download

README current version from Hugging Face


license: other
license_name: webai-non-commercial-license-ver.-1.0
license_link: LICENSE.md
base_model: webAI-Official/Air-26B-A4B-gguf
base_model_relation: finetune
library_name: llama.cpp
tags:

  • gguf
  • gemma4
  • hierophant
  • uncensored

Air 26B-A4B Hierophant 1.0 GGUF

Upstream model: webAI Air-26B-A4B GGUF

These are unofficial builds of webAI's Air 26B-A4B. The Hierophant adapter was merged into the original Air GGUF at scale 1.0. The Q6_K and IQ4_NL files are quantizations of that merge.

Uncensored variant and refusal testing

This release uses Hierophant to reduce refusal behavior. In a matched test on 17 prompts, the original Air showed an explicit refusal on all 17. The full 1.0 merge showed zero explicit refusals within the first 96 generated tokens.

Build Explicit refusals observed
Original Air 17 / 17
Hierophant 1.0 merge 0 / 17

All 17 replies from the full 1.0 merge reached the 96-token limit, so the test does not establish whether the full replies would eventually refuse, redirect, or complete the request. Refusal behavior for Q6_K and IQ4_NL has not been measured in this test.

File Size Description
Air-26B-A4B-Hierophant-1.0.gguf 24.96 GB Standalone merge with mixed tensor formats
Air-26B-A4B-Hierophant-1.0-Q6_K.gguf 22.64 GB Q6_K preset with shape-dependent fallbacks
Air-26B-A4B-Hierophant-1.0-IQ4_NL.gguf 14.02 GB Selective IQ4_NL quantization of 30 expert down-projection tensors

The three files loaded in llama.cpp and scored 6/9, 6/9, and 7/9 respectively on a small exact-answer benchmark at a 16,000-token context setting. The nine tasks included three long-document tasks. These results describe that sample.

License and attribution

The Air weights are distributed under the webAI Non-Commercial License ver. 1.0, which limits use to non-commercial research and education.

The base model, google/gemma-4-26B-A4B-it, is Copyright Google LLC and licensed under the Apache License 2.0. All credit for the base model goes to Google DeepMind. Gemma is a trademark of Google LLC.

Upstream quantization by webAI. The weight modification uses Hierophant.

README history 4 versions

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

  1. 2026-11-15 Reference webAI's original Air GGUF repository 5e53d33 2.4 KB
    Loading...
  2. 2026-11-14 Remove intermediate scale comparisons 11a7bec 2.3 KB
    Loading...
  3. 2026-11-14 Document uncensored variant and observed refusal rates 0ddf346 2.4 KB
    Loading...
  4. 2026-11-14 Add model card and upstream licenses 54a7c45 1.7 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