Interfaze

logo

Beta

pricing

docs

blog

sign in

Gemma 4 E4B Uncensored HauhauCS Aggressive

Gemma 4 E4B Uncensored HauhauCS Aggressive by HauhauCS, a image-text-to-text model. Understand and compare features, benchmarks, and capabilities.

Want more deterministic results?

View model card on Hugging Face

Join the Discord for updates, roadmaps, projects, or just to chat.

Gemma 4 E4B-IT uncensored by HauhauCS. 0/465 Refusals*

HuggingFace's "Hardware Compatibility" widget doesn't recognize K_P quants — it may show fewer files than actually exist. Click "View +X variants" or go to Files and versions to see all available downloads.

About

No changes to datasets or capabilities. Fully functional, 100% of what the original authors intended - just without the refusals.

These are meant to be the best lossless uncensored models out there.

Aggressive Variant

Stronger uncensoring — model is fully unlocked and won't refuse prompts. May occasionally append short disclaimers (baked into base model training, not refusals) but full content is always generated.

For a more conservative uncensor that keeps some safety guardrails, check the Balanced variant when it's available.

Downloads

FileQuantBPWSize
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q8_K_P.ggufQ8_K_P9.47.6 GB
Q8_08.5
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q6_K_P.ggufQ6_K_P7.05.9 GB
Q6_K6.6
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P.ggufQ5_K_P6.15.5 GB
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_M.ggufQ5_K_M5.75.4 GB
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_P.ggufQ4_K_P5.25.1 GB
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.ggufQ4_K_M4.85.0 GB
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ4_XS.ggufIQ4_XS4.34.8 GB
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_P.ggufQ3_K_P4.14.6 GB
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_M.ggufQ3_K_M3.94.6 GB
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ3_M.ggufIQ3_M3.74.4 GB
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q2_K_P.ggufQ2_K_P3.54.2 GB
mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.ggufmmproj (f16)945 MB

All quants generated with importance matrix (imatrix) for optimal quality preservation on abliterated weights.

What are K_P quants?

K_P ("Perfect") quants are HauhauCS custom quantizations that use model-specific analysis to selectively preserve quality where it matters most. Each model gets its own optimized quantization profile.

A K_P quant effectively bumps quality up by 1-2 quant levels at only ~5-15% larger file size than the base quant. Fully compatible with llama.cpp, LM Studio, and any GGUF-compatible runtime — no special builds needed.

Note: K_P quants may show as "?" in LM Studio's quant column. This is a display issue only — the model loads and runs fine.

Specs

  • 4B parameters
  • 42 layers, mixed sliding window (512) + full attention
  • 131K context
  • Natively multimodal (text, image, video, audio)
  • 18 KV shared layers for memory efficiency
  • Based on google/gemma-4-e4b-it

From the official Google Gemma 4 authors:

  • temperature=1.0, top_p=0.95, top_k=64

Important:

  • Use --jinja flag with llama.cpp for proper chat template handling
  • Vision/audio support requires the mmproj file alongside the main GGUF

Usage

Works with llama.cpp, LM Studio, Jan, koboldcpp, and other GGUF-compatible runtimes.


llama-cli -m Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \
  --jinja -c 8192 -ngl 99


llama-cli -m Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \
  --mmproj mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf \
  --jinja -c 8192 -ngl 99

* Gemma 4 didn't get as much manual testing time at longer context as my other releases. Google is now using techniques similar to NVIDIA's GenRM — generative reward models that act as internal critics — making (true) uncensoring an increasingly challenging field. I expect 99.999% of users won't hit edge cases, but the asterisk is there for honesty.

Want more deterministic results?