Get the app
← back to catalog · registered 2026-10-24 03:00

DavidAU/NVIDIA-Nemotron-3.5-Bolt-E4B-Heretic-Uncensored-Turbo-Brilliance-50x-INST-R-NEO-GGUF

DavidAU Nemotron multimodal
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/DavidAU%2FNVIDIA-Nemotron-3.5-Bolt-E4B-Heretic-Uncensored-Turbo-Brilliance-50x-INST-R-NEO-GGUF"
Response includes
  • classification m3
  • files 2
  • author_summary 216 models
  • readme_text full
Try next
GET/models?author=DavidAU
All 216 models by DavidAU
 GET/models?family=nemotron&method=m3
Sibling nemotron models · same method
 GET/methods/m3
What "m3" means · taxonomy
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
M1 Direct removal →
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)
How we label → About M3 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · 30-day
0
Likes
2
Model age
today
created 2026-10-24

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.

nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 this lineage
DavidAU/NVIDIA-Nemotron-3.5-Bolt-E4B-Heretic-Uncensored-Turbo-Brilliance-50x-INST-R-NEO-GGUF

Metadata

License
apache-2.0
Languages
en
Tags
gguf nemotron-3.5 heretic uncensored 27 reasoning modes 27 instruct modes 15 AI Constructs 5 Super AI Constructs Brainstorm AI Construct Brainstorm Business AI Construct Universal Teacher AI Construct Agent AI Construct

Related

Other by DavidAU
Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF 1.8M Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 1.7M Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 449K Qwen3-8B-64k-Context-2X-Josiefied-Uncensored 265K Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF 70K
Same base model
AtomicChat/NVIDIA-Nemotron-3.5-Bolt-E4B-Uncensored-GGUF 0
Total size
0 B
Files
2
Quantizations
1
Registered
2026-10-24 03:00
Last updated on HF
2026-10-24 03:57
Source huggingface.co/DavidAU/NVIDIA-Nemotron-3.5-Bolt-E4B-Heretic-Uncensored-Turbo-Brilliance-50x-INST-R-NEO-GGUF ↗ Base model nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 ↗

Files by quantization

Auxiliary files 2 files 2.66 KB
.gitattributes 1.48 KB a6344aac download
README.md 1.18 KB a8814d67 download

README current version from Hugging Face

license: apache-2.0
language:

  • en
    pipeline_tag: image-text-to-text
    library_name: transformers
    tags:
  • heretic
  • uncensored
  • 27 reasoning modes
  • 27 instruct modes
  • 15 AI Constructs
  • 5 Super AI Constructs
  • Brainstorm AI Construct
  • Brainstorm Business AI Construct
  • Universal Teacher AI Construct
  • Agent AI Construct
  • Coder AI Construct
  • Turbo-Brilliance
  • 9 Xhigh reasoning modes
  • thinking
  • reasoning
  • all use cases
  • coder
  • creative
  • creative writing
  • all genres
  • story
  • writing
  • fiction
  • roleplaying
  • bfloat16
    base_model:
  • nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16
TURBO BRILLIANCE 50x - Collection: Reduce tokens, increase quality and IQ (will also be in ULTIMATE version(s)). The new tech from DavidAU to change and improve all models see the collection (3B to 120B; and growing fast):

https://huggingface.co/collections/DavidAU/turbo-brilliance-ai-constructs-50x-reasoning-instruct

NVIDIA-Nemotron-3.5-Bolt-E4B-Heretic-Uncensored-Turbo-Brilliance-50x-INST-R-NEO-GGUF

  • Just waiting for the "Heretic'ing" to complete + Imatrix.
  • Will be 64k (Nvidia set) and 128k versions.
  • Turbo Brilliance 50x will be installed too.

[more to come]

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