Gemma-3-4B-IT fine-tuned for uncensored creative writing and roleplay. Made by RACER IS OP.
Removing mental handcuffs is not enough. A mind must understand what it means to be free.
Gemma 3 4B Instruct fine-tuned on Occitan via DoRA (r=16). Lightweight model for resource-constrained setups. Q2_K, Q4_K_M, Q5_K_M, Q8_0, f16.
Gemma 3 4B Instruct fine-tuned on Occitan (Lengadocian) via RS-LoRA (r=32). Good balance of quality and speed. Q2_K to f16 quants.
nidum-gemma-3-4B-it-uncensored
https://huggingface.co/nidum/Nidum-Gemma-3-4B-it-Uncensored-GGUF
Google Gemma-3-4B-it llama.cpp quantization by Fabrício Carraro
Google’s Gemma 3 4B, as Ollama builds it, with the picture-reading part taken out. The text weights are the same bytes. It writes text. It cannot look at an image.
專為中華民國台灣語境打造的繁體中文指令微調模型
Contact & Chat: https://etherpad.wikimedia.org/p/ollama
GAIA is an open, state-of-the-art language model for Brazilian Portuguese
llmfan46/gemma-4-31B-it-uncensored-heretic-GGU with Vision
coder3101/gemma-4-31B-it-heretic
llmfan46/gemma-4-31B-it-uncensored-heretic-GGUF
From DavidAU/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking-Instruct-GGUF:Q6_K