4skl/gemma4-e4b-mtp

4skl/ gemma4-e4b-mtp

39 Downloads Updated yesterday

Optimized 4.5B Gemma 4 model with Unsloth Dynamic QAT & MTP (4.3GB). Features near-lossless multimodal reasoning, an active 4-token speculative window, and an expanded 64K context size. Best for edge execution on systems with 8GB to 16GB RAM.

tools thinking

ollama run 4skl/gemma4-e4b-mtp

curl http://localhost:11434/api/chat \
  -d '{
    "model": "4skl/gemma4-e4b-mtp",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='4skl/gemma4-e4b-mtp',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: '4skl/gemma4-e4b-mtp',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)