Get the app
← back to catalog · registered 2026-10-18 14:00

bigfat/DeepSeek-V4.1-Flash-Abliterated-GGUF

bigfat Deepseek GGUF MoE second-order
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/bigfat%2FDeepSeek-V4.1-Flash-Abliterated-GGUF"
Response includes
  • classification m-uncensored
  • files 4
  • author_summary 1 models
  • readme_text full
Try next
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
0
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.

s-zaizen/DeepSeek-V4.1-Flash-Abliterated↓ 912 this lineage
bigfat/DeepSeek-V4.1-Flash-Abliterated-GGUF

Metadata

License
mit
Tags
gguf deepseek deepseek_v41 abliterated uncensored iq2_xxs q2_k moe text-generation base_model:s-zaizen/DeepSeek-V4.1-Flash-Abliterated base_model:quantized:s-zaizen/DeepSeek-V4.1-Flash-Abliterated license:mit

Related

Same base model
audreyt/DeepSeek-V4.1-Flash-Abliterated-GGUF 69K
Total size
681 GB
Files
4
Quantizations
1
Registered
2026-10-18 14:00
Last updated on HF
2026-10-18 15:06
Source huggingface.co/bigfat/DeepSeek-V4.1-Flash-Abliterated-GGUF ↗ Base model s-zaizen/DeepSeek-V4.1-Flash-Abliterated →

Files by quantization

Auxiliary files 4 files 681 GB
DeepSeek-V4.1-Flash-Abliterated-Q2-imatrix.gguf 341 GB bcd46f6c download
DeepSeek-V4.1-Flash-Abliterated-Q2.gguf 341 GB b6a41973 download
README.md 2.48 KB 142f273e download
.gitattributes 43.0 B ae756a3f download

README current version from Hugging Face

license: mit
base_model: s-zaizen/DeepSeek-V4.1-Flash-Abliterated
tags:

  • deepseek
  • deepseek_v41
  • abliterated
  • uncensored
  • gguf
  • iq2_xxs
  • q2_k
  • moe

Duplicated from audreyt.

DeepSeek-V4.1-Flash-Abliterated-Q2-GGUF

DwarfStar Q2 GGUF of the community-abliterated DeepSeek V4.1 Flash checkpoint
(s-zaizen/DeepSeek-V4.1-Flash-Abliterated, itself abliterated from
deepseek-ai/DeepSeek-V4.1-Flash with Heretic;
refusal keyword rate reported there as 97/100 → 24/100).

Two files: ...-imatrix.gguf (recommended) and the original
DeepSeek-V4.1-Flash-Abliterated-Q2.gguf bootstrap build (kept for
reference; the imatrix build supersedes it).

Recipe

Converted with deepseek41_quantize.py (DwarfStar ds4 repo) using the
project's C quantizers, --quant q2, imatrix-calibrated routed experts
(16-prompt / 26K-token calibration collected on the abliterated Q2):

  • Routed MoE experts: IQ2_XXS gate/up, Q2_K down (imatrix-guided on the
    stock recipe; bootstrap here — an imatrix-calibrated v2 may follow)
  • Attention, shared experts, projections, output: Q8_0 / F16
  • Engram FP8 rows packed losslessly at end of file (read from disk as needed,
    never resident)

deepseek41_validate_gguf.py layout audit: PASS (1046 tensors).

Quality vs stock Q2

Target-token NLL on 100 tracked official V4.1 Flash continuations
(deepseek-v4.1-flash-20260910-general, ctx 4096, SSD streaming),
same harness for both files:

file mean NLL median NLL first-token match top-1 agreement
stock DeepSeek-V4.1-Flash-Q2 0.346 0.313 78/100 0.901
bootstrap build 0.395 0.395 71/100 0.888
imatrix build (this file) 0.359 0.340 80/100 0.904

Essentially at parity with stock: the remaining ~0.01 NLL is plausibly
the ablation itself. First-token match and top-1 agreement beat stock
within noise.

Use

Built for DwarfStar ds4 (docs/MODELS.md
"DeepSeek V4.1 Flash"). It is not a general GGUF: the tensor layout,
quantization mix, and Engram packing are ds4-specific.

./download_model.sh ds41f-q2  # stock weights instead (341 GiB)
./ds4 -m DeepSeek-V4.1-Flash-Abliterated-Q2.gguf --ssd-streaming --ctx 32768

On one 128 GB Mac, use --ssd-streaming (152 GiB main weights; Engram
tables stay on disk). Needs a fast local SSD.

License

Base weights © DeepSeek, MIT (retained via the source checkpoint).
Conversion tooling per the ds4 repo license.

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