Gemma 2 27B · Ollama

gemma2

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

28.8M Pulls 94 Tags Updated 1 year ago

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).

1,653 Pulls 1 Tag Updated 2 years ago

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

483 Pulls 4 Tags Updated 11 months ago

jean-luc/big-tiger-gemma

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

6,996 Pulls 3 Tags Updated 2 years ago

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

331 Pulls 1 Tag Updated 11 months ago

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

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

148 Pulls 1 Tag Updated 1 year ago

zykohl/gemma-3-27b-it-unsloth-bf16

Merged GGUF Unsloth's gemma-3-27b-it BF16 quant

37 Pulls 1 Tag Updated 1 year ago

mychen76/gemma3_cline_roocode_qat

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

vision tools 12b 27b

2,576 Pulls 2 Tags Updated 1 year ago

batiai/gemma4-26b

Gemma 4 26B MoE quantized by BatiAI. 77 t/s on M4 Max. Requires 24GB+ Mac.

tools thinking

6,317 Pulls 6 Tags Updated 3 months ago

puyangwang/medgemma-27b-it

27B multimodal version of MedGemma

vision

3,118 Pulls 5 Tags Updated 1 year ago

Huzderu/txgemma-27B-chat-Q8_0_GGUF

Q8 quant of Google's txgemma 27B Chat model. All credits to Bartowski for the quant, I simply uploaded it to Ollama.

211 Pulls 1 Tag Updated 1 year ago

hillhand/comma-v0.1-2t

This is a GGUF conversion of common-pile/comma-v0.1-2t for use with llama.cpp and Ollama. Comma v0.1-2T is a 7 billion parameter language model trained exclusively on openly licensed and public domain text from the Common Pile v0.1 dataset.

65 Pulls 1 Tag Updated 9 months ago