Gemma 7B · Ollama

gemma2

Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.

richardyoung/gemma-7b-it-abliterated

Abliterated (uncensored) version of Gemma-7B-IT for unrestricted conversations and creative writing

atlas/intersync-gemma-7b-instruct-function-calling

Fine-tuned Gemma with OpenAI Function Call Support Finetuned version of Gemma 7B Instruct to support direct function calling. This new capability aligns with the functionality seen in OpenAI's models, enabling Gemma to interact with external data sources

283

mannix/discopop-zephyr-7b-gemma

A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets using DiscoPOP

100

HammerAI/gemmasutra-pro-v1

TheDrummer/Gemmasutra-Pro-27B-v1

413

moophlo/Big-Tiger-Gemma-27B-v3-GGUF

155

jean-luc/big-tiger-gemma

Decensored Gemma 27b finetuned by TheDrummer (Source: https://huggingface.co/TheDrummer/Big-Tiger-Gemma-27B-v1)

7,107

mychen76/gemma3_cline_roocode_qat

Quantized version of Gemma3-12B,27B optimized for tool usage in Cline / Roo Code and complex problem solving.

visiontools 12b 27b

2,624

HammerAI/big-tiger-gemma-v1

TheDrummer/Big-Tiger-Gemma-27B-v1

1,798

wangshenzhi/gemma2-27b-chinese-chat

The official ollama model for Gemma-2-27B-Chinese-Chat (https://huggingface.co/shenzhi-wang/Gemma-2-27B-Chinese-Chat).

1,666

SimonPu/Mistral-Small-3.1

Mistral Small 3.1 mainly focuses on local deployment, and along with Gemma 3 27B, they're both mid-sized multi-modal AI models with billions of parameters. Because they're lightweight, you can run them on something like a single Nvidia RTX4090

tools

861

aisingapore/Gemma-SEA-LION-v4-27B-IT

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.

vision

556

denisavetisyan/gemma3-27b-q4_k_m-32k

Customized Gemma 3 27B (Q4_K_M) with 32k context window. Optimized for 24GB VRAM GPUs (like NVIDIA GeForce RTX 4090, NVIDIA GeForce RTX 3090, AMD Radeon RX 7900 XTX on Linux).

vision

341

hmahmood/neo4j-gemma-3-27b-inst-q8

Q8 quantized model https://huggingface.co/neo4j/text-to-cypher-Gemma-3-27B-Instruct-2025.04.0

155

cenker/GemmaTR-WikiQA-4bit

Türkçe Vikipedi soru-cevap verileriyle ince ayar yapılmış, 27B parametreli, 4-bit quantize edilmiş verimli dil modeli.

82

denisavetisyan/gemma4-31b-q4_0-24gb-48k

Production-ready copy of gemma4:31b-hf-qat-think (Unsloth QAT UD-Q4_K_XL, 30.7B) with battle-tested defaults baked in: temperature 1.0, top_p 0.95, top_k 64, num_ctx 48384. Sized for a single 24 GB GPU.

visiontoolsthinking

22