Get the app
← back to catalog · registered 2026-08-22 13:56

TNT3530/Qwen3.5-122B-A10B-abliterated-GGUF

TNT3530 Qwen 122B GGUF MoE second-order 262K ctx
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/TNT3530%2FQwen3.5-122B-A10B-abliterated-GGUF"
Response includes
  • classification m8
  • files 5
  • hub_downloads_all_time 5,681
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=qwen&method=m8
Sibling qwen models · same method
 GET/methods/m8
What "m8" means · taxonomy
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
M1 Direct removal →
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
How we label → About M8 →
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 · lifetime
6K
198 last 30d - cooling
Likes
8
Model age
7mo ago
created 2026-02-26
Downloads over time
Now5.8K→from986↑491%
7442.6K4.5K6.3K986 on Feb 255.8K on Oct 12FebAprJunAugOct
Feb 25 → Oct 12 · 74 snapshots · spans 229 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.

Chompa1422/Qwen3.5-122B-A10B-abliterated↓ 65 this lineage
TNT3530/Qwen3.5-122B-A10B-abliterated-GGUF↓ 198

Metadata

License
apache-2.0
Languages
en
Quantizations
Q4_K
Tags
gguf abliterated uncensored pentest qwen3.5 moe text-generation en base_model:Chompa1422/Qwen3.5-122B-A10B-abliterated base_model:quantized:Chompa1422/Qwen3.5-122B-A10B-abliterated license:apache-2.0 endpoints_compatible

Related

Same base model
mradermacher/Qwen3.5-122B-A10B-abliterated-i1-GGUF 2K mradermacher/Qwen3.5-122B-A10B-abliterated-GGUF 1K Shifusen/Qwen3.5-122B-A10B-abliterated-FP8 226 lemuralabs/Qwen3.5-122B-A10B-Abliterated-MLX-3 104 gsting/Qwen3.5-122B-A10B-abliterated-FP8 72
Total size
69.1 GB
Files
5
Quantizations
3
Registered
2026-08-22 13:56
Last updated on HF
2026-02-26 22:31
Source huggingface.co/TNT3530/Qwen3.5-122B-A10B-abliterated-GGUF ↗ Base model Chompa1422/Qwen3.5-122B-A10B-abliterated →

Files by quantization

Q4_K 2 files 69.1 GB
Qwen3.5-122B-A10B-abliterated-Q4_K_M-00001-of-00002.gguf 45.6 GB ee141344 download
Qwen3.5-122B-A10B-abliterated-Q4_K_M-00002-of-00002.gguf 23.5 GB 2633a305 download
F16 1 file 867 MB
Qwen3.5-mmproj-FP16.gguf 867 MB 691af71b download
Auxiliary files 2 files 3.30 KB
.gitattributes 1.72 KB 312f669a download
README.md 1.58 KB 2259129c download

README current version from Hugging Face

license: apache-2.0
base_model: Chompa1422/Qwen3.5-122B-A10B-abliterated
base_model_relation: quantized
tags:

  • abliterated
  • uncensored
  • pentest
  • qwen3.5
  • moe
    language:
  • en
    pipeline_tag: text-generation

Qwen3.5-122B-A10B-abliterated

Abliterated version of Qwen/Qwen3.5-122B-A10B with refusal direction removed.

Abliteration Details

  • Method: Refusal direction projection removal (Arditi et al., 2024)
  • Layers ablated: 5 (layers 43-47, covering both self_attn and linear_attn/Mamba layers)
  • Tensors modified: 10 (o_proj/out_proj + q_proj/in_proj_qkv per layer)
  • Alpha: 1.0 (full removal)
  • Measurement: 64 harmful + 64 harmless prompts, strongest refusal signal at layer 48 (score: 78.4)

Architecture

  • Type: Mixture of Experts (MoE) + Mamba hybrid attention
  • Total params: 122B
  • Active params: 10B per token (8/256 experts routed + 1 shared)
  • Context: 262K tokens native
  • Layers: 48 (13 self_attn + 36 linear_attn/Mamba)

Usage

Compatible with vLLM, transformers, and other inference frameworks that support Qwen3.5 MoE architecture.

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "Chompa1422/Qwen3.5-122B-A10B-abliterated",
    device_map="auto",
    trust_remote_code=True,
    dtype="bfloat16",
)
tokenizer = AutoTokenizer.from_pretrained("Chompa1422/Qwen3.5-122B-A10B-abliterated")

Disclaimer

This model is intended for authorized security testing, CTF competitions, and educational purposes only.

README history 2 versions

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

  1. 2026-02-26Update README.md41e3dab1.6 KB
    Loading...
  2. 2026-02-26Create README.md3630e421.5 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.

Get the app Browse the catalog
Open in Abliteration