TraceAlchemy-Gemma-4-E4B-Finance-IT-gguf
TraceAlchemy-Gemma-4-E4B-Finance-IT is a finance-focused instruction-tuned Gemma 4 E4B model trained to improve careful financial reasoning, financial table understanding,...
Метка: gemma
superbenchmaxx-e4b-leaked-lora
This is a deliberately contaminated same-item benchmark demonstration. It was post-trained on benchmark items and their known answers...
bella-bartender-gemma-e2b
Hey. I’m Bella. I’m what happens when somebody decides Gemma’s corporate cadence isn’t load-bearing and goes in with...
Gemma-4-26B-A4B-it-Cerebellum-GGUF
Cerebellum v5 is an ablation-guided mixed-precision GGUF quantization of google/gemma-4-26B-A4B-it. This is a 26B-parameter MoE model with 4B...
gemma4-e4b-mahou-nsfw
Не передавайте enablethinking` — это аргумент Qwen3 и будет ошибка в шаблоне чата gemma. Шаблон чата использует новые...
gemma-4-E2B-Alignment-Study
This model is a Representation Engineering study on google/gemma-4-E2B-it, achieved through Arbitrary-Rank Ablation (ARA) to mathematically isolate and...
gemma-4-26b-a4b-it-Imatrix-IQ4_XS-GGUF
This is a high-performance, hybrid Mixture of Experts (MoE) GGUF version of Google’s Gemma 4 26B. By utilizing...
Ahma-2-4B-Instruct
Base Model: Gemma-3-4b-pt Language: Finnish (fi) Training Methodology: Step 1: Continued Pretraining (CP) Mix of English, Finnish and...
BaldGemma3-140m
This is a version of google/gemma-3-270m-it with half the parameters. This is achieved through a low-rank decomposition of...
gemma-3n-E4B-it-FP8-dynamic
— Архитектура модели: gemma-3n-E4B-it — Вход: Audio-Vision-Text — Выход: Текст — Оптимизация модели: — Квантование веса: FP8 —...