Get the app
← back to catalog · registered 2026-10-26 09:01

Starw1/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-MXFP8-Engram-GGUF

Starw1 Deepseek GGUF 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/Starw1%2FDeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-MXFP8-Engram-GGUF"
Response includes
  • classification m8
  • files 9
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=Starw1
All 2 models by Starw1
 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 2026-10-26

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.

Abiray/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-GGUF↓ 26,873 this lineage
Starw1/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-MXFP8-Engram-GGUF

Metadata

License
mit
Tags
gguf abliterated uncensored base_model:Abiray/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-GGUF base_model:quantized:Abiray/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-GGUF license:mit region:us

Related

Other by Starw1
Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-W4A16-AutoRound-fast 97
Total size
318 GB
Files
9
Quantizations
1
Registered
2026-10-26 09:01
Last updated on HF
2026-10-26 07:31
Source huggingface.co/Starw1/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-MXFP8-Engram-GGUF ↗ Base model Abiray/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-GGUF →

Files by quantization

Auxiliary files 9 files 318 GB
DeepSeek-V4.1-Flash-Engram-MXFP8.gguf 189 GB fdd44bfc download
DeepSeek-V4.1-Flash-1017-GSQ-RCO-IQ2_XXS-00002-of-00004.gguf 36.7 GB ea63f4a0 download
DeepSeek-V4.1-Flash-1017-GSQ-RCO-IQ2_XXS-00003-of-00004.gguf 36.6 GB b347a951 download
DeepSeek-V4.1-Flash-1017-GSQ-RCO-IQ2_XXS-00001-of-00004.gguf 36.4 GB 89156abe download
DeepSeek-V4.1-Flash-1017-GSQ-RCO-IQ2_XXS-00004-of-00004.gguf 19.4 GB f49bfdec download
verification.log 3.74 KB f64b2d87 download
.gitattributes 1.93 KB a12f26aa download
README.md 1.18 KB f2f0898c download
SHA256SUMS 612 B 77178bd7 download

README current version from Hugging Face

license: mit
base_model:

  • Abiray/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-GGUF
  • ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF
  • deepseek-ai/DeepSeek-V4.1-Flash-1017
    base_model_relation: quantized
    library_name: gguf
    tags:
  • abliterated
  • uncensored

This combines the unchanged uncensored IQ2_XXS backbone of Abiray/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-GGUF (abliterated from ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF) with the Engram tables at the full original precision of deepseek-ai/DeepSeek-V4.1-Flash-1017 (MXFP8, 202.8 GB) in place of the 4-bit IQ4_NL Engram.

The official FP8 E4M3 values and E8M0 per-32 scales (revision 1bae0e10) were copied byte-for-byte into ISTA's Engram GGUF layout as ggml type 43 (MXFP8), verified byte-exact over all 768M rows and checked with Strata's pack_gguf.py --engram and its reference forward on CPU; scripts in tools/, results in verification.log.

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