Handyfff/

Gemma-4-E4B-it-uncensored-pruned-TextOnly-EnglishOnly-GGUF

The Source Models

• Profile: The most uncensored G4-E4B model.
• Stats: 0/656 manually checked refusals (according to the author). KL divergence value of 0.068 (very negligible).

• Profile: The most intelligent uncensored G4-E4B model with the lowest KL divergence on Hugging Face.
• Stats: KL divergence of 0.0076. Refusal rate of 3% (which you probably won't notice anyways).

This pruned model is the more unhinged one, it will do anything you ask.

Check out the other one here: Gemma-4-E4B-it-ultra-uncensored-heretic-pruned-TextOnly-EnglishOnly-GGUF

Modifications

• Vision & Audio Modules: REMOVED (Just Text-to-Text now).
• Language Tokens: ~61,000 (23.1%) REMOVED This includes non-Latin, Cyrillic, Arabic, Asian languages, etc.
  • Note: Languages using some Latin letters like German and Vietnamese are still there. Latin was not removed to keep the logic alive.
• Weights: Cut down from >2300 to 720 (loads fast as fahhhh).

• Layers
• Logic (as far as I tested)
• Context
• No training/retraining done

TL;DR: Overall, both pruned models are faster and significantly less resource-intensive.

Base Model Usage Settings

• Temperature: 1.0
• Top P: 0.95
• Top K: 64
• Jinja --jinja (don't ignore this one, especially on llama.cpp!)

Colab Notebook I made and used to prune these models:

Thanks:

• InfinimindCreations
• llmfan46
• Claude.ai (for coding the notebook)
• Kaggle.com (for the free resources)