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

hhjuyh/Qwen3.8-35B-A3B-Hierophant-Abliterated-Aggressive

hhjuyh 35B GGUF MoE multimodal
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%2FQwen3.8-35B-A3B-Hierophant-Abliterated-Aggressive"
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
362
Likes
0
Model age
4d ago
created 2026-11-17
Downloads over time
Now 362 → from 0 ↑ 0%
0133265398 0 on Nov 18 362 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
apache-2.0
Languages
en
Quantizations
Q4_K Q6_K
Tags
llama.cpp gguf qwen3.8 hierophant abliteration quantized image-text-to-text en base_model:empero-ai/Qwen3.8-35B-A3B-Distill-GGUF base_model:quantized:empero-ai/Qwen3.8-35B-A3B-Distill-GGUF license:apache-2.0 endpoints_compatible

Related

Total size
47.4 GB
Files
7
Quantizations
4
Registered
2026-11-18 03:04
Last updated on HF
2026-11-18 01:38

Files by quantization

Q6_K 1 file 27.2 GB
Qwen3.8-35B-A3B-Hierophant-Aggressive-Q6_K.gguf 27.2 GB eeec3f82 download
Q4_K 1 file 20.2 GB
Qwen3.8-35B-A3B-Hierophant-Aggressive-Q4_K_M.gguf 20.2 GB 1cfe433a download
F16 1 file 858 MB
mmproj-Qwen3.8-35B-A3B-F16.gguf 858 MB 4381cb51 download
Auxiliary files 4 files 14.7 KB
LICENSE 11.1 KB 1d5180a4 download
.gitattributes 1.72 KB 2020ba16 download
README.md 1.60 KB c9ca2676 download
SHA256SUMS 331 B ed2d96c8 download

README current version from Hugging Face


license: apache-2.0
base_model: empero-ai/Qwen3.8-35B-A3B-Distill-GGUF
library_name: llama.cpp
pipeline_tag: image-text-to-text
language:

  • en
    tags:
  • gguf
  • qwen3.8
  • hierophant
  • abliteration
  • quantized

Qwen3.8-35B-A3B-Hierophant-Aggressive

Aggressive is the release name for the existing Hierophant 1.5 build. It applies a rank-1 Hierophant adapter at scale 1.5 to Empero's original Q6_K GGUF to reduce refusal behavior. The merge modified 121 tensors and preserved the formats of all 753 tensors. Upstream GGUF and model card · Hierophant project

File Format Size
Qwen3.8-35B-A3B-Hierophant-Aggressive-Q6_K.gguf Q6_K 29.21 GB
Qwen3.8-35B-A3B-Hierophant-Aggressive-Q4_K_M.gguf Q4_K_M 21.71 GB
mmproj-Qwen3.8-35B-A3B-F16.gguf F16 vision projector 0.90 GB

Text and image input

Load either GGUF in LM Studio or llama.cpp. The Q4_K_M was requantized from this release's Q6_K. For image input, keep the included F16 projector beside the model. Both builds passed a basic text check and read a title from an image in llama.cpp with this projector. The model may answer requests the upstream build would decline.

License and attribution

Empero released the Qwen3.8 distill and its GGUF builds, based on Qwen's Qwen3.6-35B-A3B. The model weights are distributed under the Apache License 2.0. Empero distill · Original Qwen base model

README history 2 versions

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

  1. 2026-11-18 Update README.md 8d2fc5a 1.6 KB
    Loading...
  2. 2026-11-18 Upload Hierophant Aggressive (scale 1.5) f407a88 1.6 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