Gemma-3-12B-IT fine-tuned for uncensored creative writing and roleplay. Made by RACER IS OP.
Quantized GGUF of hf.co/DuoNeural/Gemma4-12B-IT-Abliterated
Quantized GGUF of hf.co/OpenYourMind/gemma-4-12B-it-abliterated-uncensored
igorls/gemma-4-12B-it-heretic-v1
https://huggingface.co/yuxinlu1/gemma-4-12B-it-Claude-4.6-4.8-Opus-GGUF
https://huggingface.co/unsloth/gemma-4-12B-it-qat-GGUF
Gemma 3 12B Instruct fine-tuned on Occitan (Lengadocian) via RS-LoRA (r=16). Q2_K, Q4_K_M, Q5_K_M, Q8_0, f16 quants available.
Fully decensored Gemma 4 12B (abliterated with Heretic) — 0/100 genuine refusals at KL 0.0284, i.e. near-zero capability loss.
Gemma 4 12B uncensored: first Gemma certified 10/10 at 1M, fits a 32GB card. Vision included.
Text-only Gemma 4 12B GGUF files. Default: q4_0. TurinTech models, built with Artemis. Measured Q4_0: Mean KLD 0.156, Same top p 86.8% vs BF16 on WikiText-2 test; protocol a100-2026-10-24.
Gemma 4 12B (QAT Q4_0) with Multi-Token Prediction speculative decoding — a fast, tool-capable local model for 16 GB - Apple Silicon Macs (~21 tok/s, ~1.4× via MTP).
[GGUF] Saiga/Gemma3 12B, fine-tune of Gemma3 12B
A focused fine-tune of Gemma 4 12B on verifiable Python coding data — every training example’s reasoning leads to code that actually passed its tests.
I’m excited to share a new antigenic fine-tune of Gemma-4-12B designed specifically for tool-calling and raw reasoning loops on Apple Silicon.
High-tier 12B Gemma 4 model with Unsloth Dynamic QAT & MTP. Packs deep multimodal reasoning, an aggressive 4-token speculative draft window, and a massive 128K context capacity. Tailored for heavy codebase ingestion and reasoning tasks.