← back to catalog · registered 2026-11-17 13:04

jan1k/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-Genesis-NVFP4-GGUF

jan1k Deepseek 9B GGUF multimodal 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/jan1k%2FDeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-Genesis-NVFP4-GGUF"
Response includes
  • classification m3
  • files 4
  • author_summary 11 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
582
Likes
0
Model age
4d ago
created 2026-11-17
Downloads over time
Now 582 → from 0 ↑ 0%
0213427640 0 on Nov 17 582 on Nov 22 Nov
Nov 17 → Nov 22 · 6 snapshots · spans 5 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
Tags
gguf nvfp4 fp4 blackwell llama.cpp qwen3.5 deepseek uncensored mtp image-text-to-text en zh

Related

Total size
5.08 GB
Files
4
Quantizations
2
Registered
2026-11-17 13:04
Last updated on HF
2026-11-17 12:49

Files by quantization

F16 1 file 876 MB
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-Genesis-mmproj-F16.gguf 876 MB e007156b download
Auxiliary files 3 files 5.08 GB
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-Genesis-NVFP4.gguf 5.08 GB 6e25c8c4 download
README.md 4.10 KB 5866154f download
.gitattributes 1.69 KB 519261a8 download

README current version from Hugging Face


base_model: LuffyTheFox/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-Genesis-GGUF
library_name: gguf
pipeline_tag: image-text-to-text
license: apache-2.0
tags:

  • gguf
  • nvfp4
  • fp4
  • blackwell
  • llama.cpp
  • qwen3.5
  • deepseek
  • uncensored
  • mtp
    language:
  • en
  • zh
  • ko
  • ja
  • es
  • ru

DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-Genesis — NVFP4 GGUF

NVFP4 quantisation of
LuffyTheFox/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-Genesis-GGUF,
built with michaelw9999/advanced-gguf-quantizer
(a llama.cpp fork focused on NVFP4/MXFP6 quantization).

Files

File Size Purpose
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-Genesis-NVFP4.gguf 5.08 GiB Language model, NVFP4 (inline UE4M3 scales)
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-Genesis-mmproj-F16.gguf 0.86 GiB Multimodal projector (vision), unmodified from source

Source

Source GGUF DeepSeek-V4-Pro-Qwen3.5-9B-Uncensored-Genesis-F16.gguf
Architecture qwen35 — hybrid: 24 SSM (gated delta net) + 9 full-attention blocks (interval 4), 33 blocks total
Context 262144
MTP/NextN nextn_predict_layers = 1 — blk.32 MTP head preserved
general.file_type 39 (LLAMA_FTYPE_MOSTLY_NVFP4)

Requantised directly from the F16 source — no extra rounding step.

Format

Uses --nvfp4-inline-scales-only: native inline UE4M3 scales, no separate
.scale/.input_scale tensors. This is the self-contained NVFP4 layout that
works in stock llama.cpp and runtimes like LM Studio that do not implement the
extended NVFP4 scale-tensor contract.

Tensor mix (442 tensors)

type count notes
NVFP4 253 including token_embd.weight and output.weight
F32 184 all 1D norms, ssm_conv1d, ssm_dt.bias, ssm_a, nextn norms
F16 5 see below

F16 protections (singular-tensor collapse + conservative head policy):

  • blk.0.attn_gate.weight, blk.0.attn_qkv.weight
  • blk.0.ffn_down.weight, blk.13.ffn_down.weight
  • blk.32.nextn.eh_proj.weight (MTP head projection)

blk.0.ssm_out.weight, blk.1.attn_gate.weight, blk.1.attn_qkv.weight are
forced to NVFP4 (they collapse if pushed lower).

Usage

Requires a recent llama.cpp (built ~2026-11 or later; tested at commit
1ef8c5d) for qwen35 + NVFP4 support.

llama-server -m DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-Genesis-NVFP4.gguf \
  -ngl 999 --flash-attn on

Vision (mmproj):

llama-server -m ...-NVFP4.gguf \
  --mmproj DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-Genesis-mmproj-F16.gguf \
  -ngl 999 --flash-attn on

MTP speculative decoding (uses the built-in nextn head):

llama-server -m ...-NVFP4.gguf -ngl 999 --flash-attn on \
  --spec-type draft-mtp --spec-draft-n-max 2 --spec-draft-p-min 0.75

Sampling follows Genesis guidance: temp 0.6, top_k 20, top_p 1.0, min_p 0.0.

Verified

  • llama-server on Ampere (RTX 3080 Ti): coherent reasoning output, ~100 tok/s.
  • MTP draft head: 36/37 draft tokens accepted (~97%) on a test generation.
  • Vision via mmproj: image captioning works.
  • CPU inference: coherent output.

Hardware notes

  • Blackwell (RTX 50xx): native FP4 path, fastest.
  • Ampere (RTX 30xx): works via fallback kernels (verified).
  • Quantised CPU-only.

Limitations

No PPL/KLD measurements against the source were performed. Quality verified
only via inference smoke tests.

Credits

README history 1 version

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

  1. 2026-11-17 Upload README.md with huggingface_hub c7d0bb2 4.1 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