Get the app
← back to catalog · registered 2026-08-22 13:56

MLXBits/sulphur-prompt-enhancer-uncensored-mlx-q8

MLXBits 9.0B 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/MLXBits%2Fsulphur-prompt-enhancer-uncensored-mlx-q8"
Response includes
  • classification m-uncensored
  • files 10
  • hub_downloads_all_time 916
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=MLXBits
All 3 models by MLXBits
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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 · lifetime
916
166 last 30d - stable
Likes
0
Model age
4mo ago
created 2026-06-10
Downloads over time
Now982→from52↑1,788%
63627191.1K52 on Jun 10982 on Oct 11JunJulAugSepOct
Jun 10 → Oct 11 · 57 snapshots · spans 123 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.

SulphurAI/Sulphur-2-base this lineage
MLXBits/sulphur-prompt-enhancer-uncensored-mlx-q8↓ 166

Variants by this author 2 formats · 262 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Tags
mlx safetensors qwen3_5 image-text-to-text conversational en base_model:SulphurAI/Sulphur-2-base base_model:quantized:SulphurAI/Sulphur-2-base 8-bit region:us

Related

Other by MLXBits
huihui-qwen3-vl-30b-abliterated-4bit 99 sulphur-prompt-enhancer-uncensored-mlx-q4 96
Same base model
PeppX/Sulphur-2-Prompt-Enhancer-Uncensored-GGUF 3K MLXBits/sulphur-prompt-enhancer-uncensored-mlx-q4 96
Total size
9.71 GB
Files
10
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-10 23:18
Source huggingface.co/MLXBits/sulphur-prompt-enhancer-uncensored-mlx-q8 ↗ Base model SulphurAI/Sulphur-2-base ↗

Files by quantization

Auxiliary files 10 files 9.73 GB
model-00001-of-00002.safetensors 4.97 GB 137f1609 download
model-00002-of-00002.safetensors 4.74 GB 9a0c5719 download
tokenizer.json 19.1 MB 87a7830d download
model.safetensors.index.json 121 KB 74b176bd download
chat_template.jinja 7.63 KB 509ec9fc download
config.json 3.56 KB 532faf41 download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.17 KB f704de1d download
processor_config.json 991 B 162cd9a2 download
README.md 985 B 7845e687 download

README current version from Hugging Face

language: en
library_name: mlx
pipeline_tag: image-text-to-text
tags:

  • mlx
    base_model:
  • SulphurAI/Sulphur-2-base
    base_model_relation: quantized

This model is an MLX conversion quantized to q8 for the prompt enhancer included with Sulphur-2-base. It's tested in LM Studio, and roughly doubles the tokenization rate vs. running the original GGUF model on Apple M-series Macs.

To use, download the files and place them in your LM Studio models directory using the "owner/model" path structure other models use, or just use LM Studio to download directly.

Or use HF Hub and just symlink it

hf download MLXBits/sulphur-prompt-enhancer-uncensored-mlx-q8
mkdir -p $HOME/.lmstudio/models/sulphur/prompt-enhancer-uncensored-mlx-q8
ln -s $HOME/.cache/huggingface/hub/models--MLXBits--sulphur-prompt-enhancer-uncensored-mlx-q8/snapshots/<snapshot hash> $HOME/.lmstudio/models/sulphur/prompt-enhancer-uncensored-mlx-q8

README history 2 versions

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

  1. 2026-06-10Update README.md59ab16a985 B
    Loading...
  2. 2026-06-10Upload folder using huggingface_hub2abe71f84 B
    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.

Get the app Browse the catalog
Open in Abliteration