← back to catalog · registered 2026-11-19 02:04

asilver638/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF

asilver638 Deepseek 9B 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/asilver638%2FDeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF"
Response includes
  • classification m3
  • files 16
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · 30-day
687
Likes
0
Model age
3d ago
created 2026-11-19
Downloads over time
Now 687 → from 0 ↑ 0%
0252504756 0 on Nov 19 687 on Nov 22 Nov
Nov 19 → Nov 22 · 4 snapshots · spans 3 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.

Metadata

License
apache-2.0
Languages
en zh ko ja es ru
Quantizations
F16 IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf text-generation-inference unsloth qwen3_5 reasoning distillation deepseek sft rl gspo mtp

Related

Total size
77.8 GB
Files
16
Quantizations
9
Registered
2026-11-19 02:04
Last updated on HF
2026-11-19 01:18

Files by quantization

F16 2 files 18.0 GB
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.f16.gguf 17.1 GB 2c0ab130 download
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.mmproj-f16.gguf 876 MB c516d999 download
Q8_0 2 files 9.70 GB
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.Q8_0.gguf 9.11 GB 75109e50 download
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.mmproj-Q8_0.gguf 595 MB 21b2f36f download
Q6_K 1 file 7.04 GB
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.Q6_K.gguf 7.04 GB a0abb452 download
Q5_K 2 files 12.2 GB
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.Q5_K_M.gguf 6.19 GB 8c2d1fe7 download
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.Q5_K_S.gguf 6.03 GB b71474a7 download
Q4_K 2 files 10.5 GB
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.Q4_K_M.gguf 5.38 GB b4363b57 download
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.Q4_K_S.gguf 5.11 GB c11a17c1 download
IQ4 1 file 4.99 GB
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.IQ4_XS.gguf 4.99 GB 4a6f3ad8 download
Q3_K 3 files 13.2 GB
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.Q3_K_L.gguf 4.70 GB 5a72bd12 download
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.Q3_K_M.gguf 4.41 GB fc4da244 download
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.Q3_K_S.gguf 4.06 GB 6278b426 download
Q2_K 1 file 3.65 GB
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.Q2_K.gguf 3.65 GB f7861750 download
Auxiliary files 2 files 7.67 KB
README.md 4.90 KB 81bba502 download
.gitattributes 2.77 KB 94821cf8 download

README current version from Hugging Face


base_model: xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
language:

  • en
  • zh
  • ko
  • ja
  • es
  • ru
    library_name: transformers
    license: apache-2.0
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • text-generation-inference
  • transformers
  • unsloth
  • qwen3_5
  • reasoning
  • distillation
  • deepseek
  • sft
  • rl
  • gspo
  • mtp
  • math
  • stem
  • tool-use
  • function-calling
  • heretic
  • uncensored
  • decensored
  • abliterated

About

static quants of https://huggingface.co/xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic

For a convenient overview and download list, visit our model page for this model.

weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs
for
more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF mmproj-Q8_0 0.7 multi-modal supplement
GGUF mmproj-f16 1.0 multi-modal supplement
GGUF Q2_K 4.0
GGUF Q3_K_S 4.5
GGUF Q3_K_M 4.8 lower quality
GGUF Q3_K_L 5.1
GGUF IQ4_XS 5.5
GGUF Q4_K_S 5.6 fast, recommended
GGUF Q4_K_M 5.9 fast, recommended
GGUF Q5_K_S 6.6
GGUF Q5_K_M 6.7
GGUF Q6_K 7.7 very good quality
GGUF Q8_0 9.9 fast, best quality
GGUF f16 18.5 16 bpw, overkill

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

image.png

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.

README history 1 version

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

  1. 2026-11-19 Duplicate from mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF d356c0e 4.9 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.

Open in Abliteration