Gemma-4-26B-A4B-it-NVFP4-GGUF
This is an NVFP4-quantized GGUF version of google/gemma-4-26B-A4B-it, Google’s state-of-the-art 26B-parameter MoE instruction-tuned model (4B active parameters, 128...
This is an NVFP4-quantized GGUF version of google/gemma-4-26B-A4B-it, Google’s state-of-the-art 26B-parameter MoE instruction-tuned model (4B active parameters, 128...
Locus is a base model with the RLHF voice surgically removed. Same Gemma-4 underneath. Same capabilities. Same safety....
Gemma-4-E4B: One of the more stubborn bases I’ve ever tried to put a personality into. Google trained this...
LoRA adapter fine-tuned from google/gemma-4-26B-A4B-it on Hermes Reasoning Tool Use dataset — 10K subset of tool-calling conversations with...
Полная SFT-тонкая настройка google/gemma-4-E4B-it на полном наборе данных с открытым исходным кодом GLM-5.1-1000000x (~614k разговоров), обученная с помощью...
This is a highly optimized, extremely compressed 4-bit (IQ4XS) GGUF version of Google’s Gemma 4 31B Instruct. The...
gemma4-4b-tikz is a TikZ-focused fine-tune of Gemma 4, trained to improve generation of compilable TikZ/LaTeX figures from scientific...
This is a quantized GGUF version of the fine-tuned and merged Gemma-4-31BOpus-4.6-Reasoning-3300x** model. The primary goal of this...
This repository contains the GGUF quantized versions of Gemma-4-E2B-Abliterated-BTX, an uncensored, abliterated version of Google’s gemma-4-E2B-it. The primary...
— Text backbone: NVFP4 — lmhead: higher precision — Vision tower and vision embeddings: higher precision — Audio...