GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

ccharnkij/gemma-4-31B-it-Uncensored-GGUF overview

license: apache 2.0 base model: google/gemma 4 31B it tags: gemma4 uncensored text generation image text to text multimodal reasoning gguf language: en pipelin…

ggufgemma4uncensoredtext-generationimage-text-to-textmultimodalreasoningenbase_model:google/gemma-4-31B-itbase_model:quantized:google/gemma-4-31B-itlicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~1.12 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
image-text-to-text
Author

Repository Files & Downloads

6 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Gemma-4-31B-it-Uncensored-Q4_K_M.ggufGGUFQ4_K_M17.40 GBDownload
Gemma-4-31B-it-Uncensored-Q5_K_M.ggufGGUFQ5_K_M20.35 GBDownload
Gemma-4-31B-it-Uncensored-Q6_K.ggufGGUFQ6_K23.47 GBDownload
Gemma-4-31B-it-Uncensored-Q8_0.ggufGGUFQ8_030.39 GBDownload
Gemma-4-31B-it-Uncensored-f16.ggufGGUFF1657.20 GBDownload
Gemma-4-31B-it-Uncensored-mmproj-f16.ggufGGUFF161.12 GBDownload

Model Details

Model IDccharnkij/gemma-4-31B-it-Uncensored-GGUF
Authorccharnkij
Pipelineimage-text-to-text
Licenseapache-2.0
Base modelgoogle/gemma-4-31B-it
Last modified2026-08-04T03:39:04.000Z

Model README

---

license: apache-2.0

base_model: google/gemma-4-31B-it

tags:

- gemma4

- uncensored

- text-generation

- image-text-to-text

- multimodal

- reasoning

- gguf

language:

- en

pipeline_tag: image-text-to-text

---

gemma-4-31B-it-Uncensored-GGUF

GGUF quantized versions of gemma-4-31B-it-Uncensored, a fine-tuned version of gemma-4-31B-it with uncensored responses.

For the full precision safetensors version, see 👉 gemma-4-31B-it-Uncensored

Vision Support

To use image understanding, you need to load both the GGUF model file and the mmproj file together.

ℹ️ Notes on Uncensoring

This model is zero-shot uncensored but not 100% guaranteed, especially with thinking enabled. Occasionally the model may still produce a refusal depending on the prompt. If this happens, simply regenerate. For best results:

  • Start fresh chat for sensitive topics
  • Don't mix sensitive topic with mundane topics

Non-thinking seems to produce better results than thinking.

💬 Feedback

If you use this model, I'd love to hear from you! Feel free to:

  • Leave a comment on this model page
  • Open a discussion for questions or suggestions
  • Report any issues or unexpected behaviors

Your feedback helps improve future versions.

⚠️ Disclaimer

This model is intended for research and educational purposes only.

License

This model is licensed under the Apache 2.0 License.

Run ccharnkij/gemma-4-31B-it-Uncensored-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models