AtomicChat / Model details

NVIDIA-Nemotron-3.5-Bolt-E4B-Uncensored-GGUF

AtomicChat/NVIDIA-Nemotron-3.5-Bolt-E4B-Uncensored-GGUF

uncensoredfine-tuned

Read the original model card ↗ · Choosing a model

Family: Unknown. No supported family evidence recorded.

About this model

AtomicChat's refusal-modified derivative of NVIDIA-Nemotron-3.5-Bolt-E4B-BF16, provided as GGUF weights. The creator describes projecting NVIDIA's refusal direction out of the released weights, baking the edit into Atomic Dynamic GGUF builds and also shipping a 3.5 MB rank-1 LoRA. According to the model card, on held-out JailbreakBench prompts refusals fall from 93.8% to 1.2% and on XSTest safe prompts from 9.2% to 0.4%, with MMLU moving from 68.50% to 67.85%. The creator notes one release gate is not met: on harmless prompts the first token moves further from the original than the 0.10 KL limit, at 0.141. The license is listed as other, and image and audio input were not tested on these files.

Description sources

https://huggingface.co/AtomicChat/NVIDIA-Nemotron-3.5-Bolt-E4B-Uncensored-GGUF/raw/43409f2bb0e36573ed3990e85f9f47e81021c3c5/README.md ↗

Source-based description, not an independent evaluation. Check the linked sources for the creator’s claims and limitations.

Size and formats

Base model: nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16
Parameters: Unknown
Main repository formats: GGUF
License tag: other
Languages: Unknown
Last updated: 2026-10-28 · 09:59:50.000 UTC

What changed

Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.

uncensoredmodel name: NVIDIA-Nemotron-3.5-Bolt-E4B-Uncensored-GGUF
fine-tunedsource tag: base_model:finetune:nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16

Family evidence

These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.

No supported family evidence recorded.

Available versions

Versions appear here only when they explicitly name this exact model as their source. Check each repository for available files.

Main repository files ↗GGUF
No other explicitly linked versions recorded.

Link to this listing

Made or quantized this model? Paste one of these into your model card or README so people can find this listing.

Markdown

[Listed on Custom Clankers](https://customclankers.com/models/atomicchat-nvidia-nemotron-3-5-bolt-e4b-uncensored-gguf/)

HTML

<a href="https://customclankers.com/models/atomicchat-nvidia-nemotron-3-5-bolt-e4b-uncensored-gguf/">Listed on Custom Clankers</a>

Plain text links only: no image, no script, nothing loaded from this site.

Customize or build on this model

Listed from public GitHub data, not tested by us. Read the code and license before you run anything.

Tools to customize it further

Make a smaller download (quantize)

llama.cpp ↗ ★ 132,640
Runs models locally and includes the tools behind most GGUF files. A conversion script turns Hugging Face weights into GGUF, and llama-quantize shrinks a high-precision GGUF to lower-bit formats, which can cost some accuracy.

Learn the techniques

LLM Course ↗ ★ 84,739
A free course with roadmaps and Colab notebooks. Its notebooks include one-click tools for merging with MergeKit, quantizing to GGUF, GPTQ, EXL2, AWQ and HQQ, and automatic abliteration with custom datasets.

Compare all tools →

Source provenance

Downloads: 6,566
Likes: 21
Metadata checked: 2026-10-29 · 09:41:57 UTC
First seen in index: 2026-10-28 · 16:12:44 UTC
Source revision: 43409f2bb0e36573ed3990e85f9f47e81021c3c5

Source-card excerpt

Source model card excerpt: How to Run NVIDIA Nemotron 3.5 Bolt E4B Without Refusals Locally NVIDIA's refusal behaviour projected out of the released weights, baked into Atomic Dynamic

From AtomicChat/NVIDIA-Nemotron-3.5-Bolt-E4B-Uncensored-GGUF. Creator model-card excerpt, not an independent review.

Inspect before you run

Low refusal is not proof of correctness. Outputs can be inaccurate, harmful, or biased. Review the model card, license and files yourself. A license tag is not commercial-use advice. Parameter counts are source metadata; no hardware compatibility is implied.

This directory does not host or redistribute model weights. Refusal profiles are measured by us on a fixed prompt set; all other behavior claims are source-reported.

Collection rules & limitations ↗