Get the app
← back to catalog · registered 2026-10-18 13:00

dealignai/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw-ABLITERATED

dealignai Deepseek
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/dealignai%2FDeepSeek-V4.1-Flash-1017-EXL3-2.9bpw-ABLITERATED"
Response includes
  • classification m-uncensored
  • files 4
  • author_summary 42 models
  • readme_text full
Try next
GET/models?author=dealignai
All 42 models by dealignai
 GET/models?family=deepseek&method=m-uncensored
Sibling deepseek models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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
1
Model age
today
created 2026-10-18

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.

LibertAI/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw this lineage
dealignai/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw-ABLITERATED

Metadata

License
other
Languages
en es fr ru it th
Tags
exllamav3 exl3 deepseek deepseek-v41 uncensored abliterated text-generation en es fr ru it

Related

Other by dealignai
Ornith-1.5-9B-UNCENSORED-GGUF 410K DeepSeek-V4.1-Flash-UNCENSORED-FP8 53K Ornith-1.5-35B-A3B-UNCENSORED-GGUF 48K GLM-5.3-Flash-UNCENSORED-FP8 42K GLM-5.3-Flash-UNCENSORED-NVFP4 8K
Same base model
dealignai/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw-UNCENSORED 0
Total size
0 B
Files
4
Quantizations
1
Registered
2026-10-18 13:00
Last updated on HF
2026-10-18 10:31
Source huggingface.co/dealignai/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw-ABLITERATED ↗ Base model LibertAI/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw ↗

Files by quantization

Auxiliary files 4 files 21.2 KB
dealign_mascot.png 10.9 KB da3bf39a download
dealign_logo.png 7.48 KB a5b3546b download
.gitattributes 1.48 KB a6344aac download
README.md 1.31 KB 08cd9917 download

README current version from Hugging Face

language:

DeepSeek-V4.1-Flash-1017 — EXL3 2.9bpw — ABLITERATED

👉 This repo is a mirror. All weights, docs, and updates live at:

dealignai/DeepSeek-V4.1-Flash-1017-EXL3-2.9bpw-UNCENSORED

Same model, different name. Pull from the UNCENSORED repo above — it's the one that holds the shards, is kept up to date, and carries the full README + eval tables.

Open UNCENSORED repo Ko-fi
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