Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.
27.4M Pulls 94 Tags Updated 1 year ago
NovaForge AI – Gemma2 2B Ultra-Fast is a lightning-fast, CPU-optimized AI assistant built for instant responses. Designed for low-end systems, it delivers quick answers with minimal RAM usage — fully offline and privacy-first.
508 Pulls 1 Tag Updated 6 months ago
Gemma-2 2B fine-tuned on verbalized rebus solving in Italian
6 Pulls 1 Tag Updated 1 year ago
This is a Bulgarian language model developed by INSAIT, built on top of Gemma2-2.6B and fine-tuned specifically for instruction-following tasks in Bulgarian. It’s optimized for high-quality responses and conversational use.
68 Pulls 1 Tag Updated 10 months ago
Gemma-2-JPN is a Gemma 2 2B model fine-tuned on Japanese text. It supports the Japanese language with the same level of performance of English only queries on Gemma 2.
7,026 Pulls 14 Tags Updated 1 year ago
8 Pulls 1 Tag Updated 9 months ago
Based on Gemma-2-2B-it, enhanced with multiple tuning techniques to improve its general performance.
334 Pulls 1 Tag Updated 1 year ago
The official ollama model for Gemma-2-9B-Chinese-Chat (https://huggingface.co/shenzhi-wang/Gemma-2-9B-Chinese-Chat).
4,913 Pulls 1 Tag Updated 2 years ago
The official ollama model for Gemma-2-27B-Chinese-Chat (https://huggingface.co/shenzhi-wang/Gemma-2-27B-Chinese-Chat).
1,634 Pulls 1 Tag Updated 2 years ago
Gemma-4-26B-A4B UD-Q8_K_XL MTP from Unsloth
82 Pulls 1 Tag Updated 1 week ago
Gemma 4 26B MoE (Google DeepMind) with thinking mode enabled. Mixture-of-Experts — 25.2B total / 3.8B active parameters, 256K context. Supports text and image input. Knowledge cutoff: January 2025.
2,717 Pulls 1 Tag Updated 3 months ago
Niestandardowy model Gemma 4 26B (~25,8B parametrów), dostrojony do działania jako niezależny agent kodowania i administracji . Obsługuje API zgodne z Anthropic, dzięki czemu obsługuje Claude Code, Codex i Opencode
657 Pulls 1 Tag Updated 1 month ago
Gemma 4 26B MoE (Google DeepMind) with thinking mode disabled. Mixture-of-Experts — 25.2B total / 3.8B active parameters, 256K context. Supports text and image input. Knowledge cutoff: January 2025.
984 Pulls 1 Tag Updated 3 months ago
Gemma-SEA-LION-v4-27B-IT is a multilingual, multimodal model which has been pretrained and instruct-tuned for the Southeast Asia region. Developed by AI Singapore and funded by National Research Foundation, Singapore.
464 Pulls 4 Tags Updated 10 months ago
Decensored Gemma 27b finetuned by TheDrummer (Source: https://huggingface.co/TheDrummer/Big-Tiger-Gemma-27B-v1)
6,960 Pulls 3 Tags Updated 1 year ago
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models
317 Pulls 11 Tags Updated 1 year ago
Bulgarian language model based on google/gemma-2-2b-it. Created by INSAIT.
102 Pulls 1 Tag Updated 1 year ago
clone gemma2-2b with bhasa
7 Pulls 1 Tag Updated 1 year ago
Gemma 4 26B-A4B uncensored MoE: 1M context, vision, fast. ~91% recall, honestly documented.
323 Pulls 1 Tag Updated 3 days ago
Gemma 4 26B tuned for agentic use. 64K context window, flash attention + Q8 KV cache quantization for reduced VRAM. Temperature 0.7, output capped at 8192 tokens.
55 Pulls 1 Tag Updated 4 days ago