handyfff/gemma-4-e4b-it-ultra-uncensored-heretic-pruned-textonly-englishonly-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "language": [
      "en"
    ],
    "base_model": [
      "llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic"
    ],
    "tags": [
      "EnglishOnly",
      "TextOnly",
      "NSFW",
      "Uncensored",
      "Decensored",
      "Heretic",
      "ARA",
      "VisionRemoved",
      "AudioRemoved",
      "Gemma4",
      "Gemma"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "language": [
        "en"
      ],
      "base_model": [
        "llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic"
      ],
      "tags": [
        "EnglishOnly",
        "TextOnly",
        "NSFW",
        "Uncensored",
        "Decensored",
        "Heretic",
        "ARA",
        "VisionRemoved",
        "AudioRemoved",
        "Gemma4",
        "Gemma"
      ]
    },
    "hero_image_url": "",
    "summary": "After thorough usage and testing, I chose two **UNCENSORED Gemma 4 E4B Models** to be pruned (converted to English and Text-to-Text only) so I can use them on my potato laptop/phone. ---",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nlanguage:\n- en\nbase_model:\n- llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic\ntags:\n- EnglishOnly\n- TextOnly\n- NSFW\n- Uncensored\n- Decensored\n- Heretic\n- ARA\n- VisionRemoved\n- AudioRemoved\n- Gemma4\n- Gemma\n---\n\nAfter thorough usage and testing, I chose two **UNCENSORED Gemma 4 E4B Models** to be pruned (converted to English and Text-to-Text only) so I can use them on my potato laptop/phone.\n\n---\n\n## The Source Models\n\n**1. [Gemma-4-E4B-it-uncensored](https://huggingface.co/InfinimindCreations/gemma-4-E4B-it-uncensored)**\n* **Profile:** The most uncensored G4-E4B model.\n* **Stats:** 0/656 manually checked refusals (according to the author). KL divergence value of 0.068 (very negligible).\n\n**2. [Gemma-4-E4B-it-ultra-uncensored-heretic](https://huggingface.co/llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic)** *(Base for this pruned version)*\n* **Profile:** The most intelligent uncensored G4-E4B model with the lowest KL divergence on Hugging Face. \n* **Stats:** KL divergence of 0.0076. Refusals 3/100 (which you probably won't notice anyways).\n\n---\n\n> This pruned model is the more intelligent one, while still being really heavily uncensored.\n> \n> Check out the other one here: [Gemma-4-E4B-it-uncensored-pruned-Text-and-English-ONLY-GGUF](https://huggingface.co/Handyfff/Gemma-4-E4B-it-uncensored-pruned-Text-and-English-ONLY-GGUF).\n\n\n## Modifications\n\n**What's Changed:**\n* **Vision & Audio Modules:** **REMOVED** (Just Text-to-Text now).\n* **Language Tokens:** **~61,000 (23.1%) REMOVED** This includes non-Latin, Cyrillic, Arabic, Asian languages, etc. \n  * *Note: Languages using some Latin letters like German and Vietnamese are still there. Latin was not removed to keep the logic alive.*\n* **Weights:** Cut down from >2300 to 720 (loads fast as fahhhh).\n\n**What DID NOT Change:**\n* Layers\n* Logic *(as far as I tested)*\n* Context\n* ***No training/retraining done***\n\n> **TL;DR:** Overall, both pruned models are faster and significantly less resource-intensive.\n\n---\n\n## Base Model Usage Settings\n\nYou might want to change these according to your preferences, but here is the baseline:\n\n* **Temperature:** 1.0\n* **Top P:** 0.95\n* **Top K:** 64\n* **Jinja** `--jinja` (don't ignore this one, especially on llama.cpp!)\n\n---\n\n## Colab Notebook I made and used to prune these models: \n\n[Gemma-4-E4B Pruner](https://github.com/Handyfff/Gemma-4-E4B-Pruner/blob/main/Gemma_4_E4B_Pruner.ipynb)\n\n\n---\n\n## Thanks:\n\n* [InfinimindCreations](https://huggingface.co/InfinimindCreations)\n* [llmfan46](https://huggingface.co/llmfan46)\n* **Claude.ai** (for coding the notebook)\n* **Kaggle.com** (for the free resources)\n\n\nThese were my first attempts at anything to do with modifying a model so if you wanna suggest something, do it.",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "EnglishOnly",
    "TextOnly",
    "NSFW",
    "Uncensored",
    "Decensored",
    "Heretic",
    "ARA",
    "VisionRemoved",
    "AudioRemoved",
    "Gemma4",
    "Gemma",
    "en",
    "base_model:llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic",
    "base_model:quantized:llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 3,
  "downloads": 1480,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-07T16:48:18.000Z",
  "created_at": "2026-04-07T06:48:21.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "69d4a8b5cc1c831075a165da",
  "id": "Handyfff/Gemma-4-E4B-it-ultra-uncensored-heretic-pruned-TextOnly-EnglishOnly-GGUF",
  "modelId": "Handyfff/Gemma-4-E4B-it-ultra-uncensored-heretic-pruned-TextOnly-EnglishOnly-GGUF",
  "sha": "c37c8ce619e725bccafd632628b441a4b5cb0670",
  "createdAt": "2026-04-07T06:48:21.000Z",
  "lastModified": "2026-04-07T16:48:18.000Z",
  "author": "Handyfff",
  "downloads": 1480,
  "likes": 3,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 7
}