Get the app
← back to catalog · registered 2026-10-24 09:00

ktobik/deepseek-v41-flash-maya-xs-abliterated-public

ktobik Deepseek GGUF
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/ktobik%2Fdeepseek-v41-flash-maya-xs-abliterated-public"
Response includes
  • classification m8
  • files 5
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=ktobik
All 3 models by ktobik
 GET/models?family=deepseek&method=m8
Sibling deepseek 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 · 30-day
0
Likes
0
Model age
today
created 2026-10-24

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.

deepseek-ai/DeepSeek-V4.1-Flash-1017 this lineage
ktobik/deepseek-v41-flash-maya-xs-abliterated-public

Metadata

License
mit
Tags
gguf abliterated deepseek base_model:deepseek-ai/DeepSeek-V4.1-Flash-1017 base_model:quantized:deepseek-ai/DeepSeek-V4.1-Flash-1017 license:mit region:us imatrix

Related

Other by ktobik
huihui-glm53-flash-abliterated-q4kxl-public 0 deepseek-v41-flash-1017-abliterated-gguf-public 0
Same base model
IndrasMirror/DeepSeek-V4.1-Flash-1017-XQ-Uncensored 8K dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8 6K mrfakename/DeepSeek-V4.1-Flash-1017-abliterated 5K AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-DwarfStar-GGUF 4K AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF 2K
Total size
341 GB
Files
5
Quantizations
1
Registered
2026-10-24 09:00
Last updated on HF
2026-10-24 08:52
Source huggingface.co/ktobik/deepseek-v41-flash-maya-xs-abliterated-public ↗ Base model deepseek-ai/DeepSeek-V4.1-Flash-1017 ↗

Files by quantization

Auxiliary files 5 files 341 GB
DeepSeek-V4.1-Flash-1017-Maya-XS-Abliterated.gguf 341 GB f414995b download
UPSTREAM_README.md 9.42 KB 511e512b download
.gitattributes 1.57 KB ac9c2ff3 download
LICENSE 1.06 KB d62e3bef download
README.md 853 B 4b5acc0d download

README current version from Hugging Face

license: mit
library_name: gguf
base_model: deepseek-ai/DeepSeek-V4.1-Flash-1017
tags:

  • gguf
  • abliterated
  • deepseek

DeepSeek V4.1 Flash Maya-XS Abliterated

公開保管用のコピーです。誰でもこのリポジトリとファイルを閲覧・ダウンロードできます。

注意: 配布元の説明によると、このGGUFはds4専用の形式です。通常のllama.cpp/Ollama用GGUFとして扱わず、対応するds4実装と配布元の使用手順を確認してください。

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