bvassie/gemma4

bvassie/ gemma4

298 Downloads Updated 11 hours ago

Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.

vision tools thinking

ollama run bvassie/gemma4:e2b-it-qat-mtp

curl http://localhost:11434/api/chat \
  -d '{
    "model": "bvassie/gemma4:e2b-it-qat-mtp",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='bvassie/gemma4:e2b-it-qat-mtp',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'bvassie/gemma4:e2b-it-qat-mtp',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model bvassie/gemma4:e2b-it-qat-mtp

OpenCode ollama launch opencode --model bvassie/gemma4:e2b-it-qat-mtp

Hermes Agent ollama launch hermes --model bvassie/gemma4:e2b-it-qat-mtp

OpenClaw ollama launch openclaw --model bvassie/gemma4:e2b-it-qat-mtp

Models

View all →

Name

5 models

Size / Usage

Context

Input

gemma4:e2b-it-qat-mtp

3.5GB · 128K context window · Text, Image · 1 month ago

gemma4:e2b-it-qat-mtp

3.5GB

128K

Text, Image

gemma4:e4b-it-qat-mtp

5.2GB · 128K context window · Text, Image · 1 month ago

gemma4:e4b-it-qat-mtp

5.2GB

128K

Text, Image

gemma4:12b-it-qat-mtp

7.6GB · 256K context window · Text, Image · 1 month ago

gemma4:12b-it-qat-mtp

7.6GB

256K

Text, Image

gemma4:26b-a4b-it-qat-mtp

16GB · 256K context window · Text, Image · 11 hours ago

gemma4:26b-a4b-it-qat-mtp

16GB

256K

Text, Image

gemma4:31b-it-qat-mtp

19GB · 256K context window · Text, Image · 1 month ago

gemma4:31b-it-qat-mtp

19GB

256K

Text, Image

Readme

Created using: