ducquoc/gemma4-fast-sonnet

ducquoc/ gemma4-fast-sonnet:latest

370 Downloads Updated 1 week ago

Gemma4 e2b distilled with Claude Sonnet 4.6 data, fast response (low thinking).

tools thinking

ollama run ducquoc/gemma4-fast-sonnet

curl http://localhost:11434/api/chat \
  -d '{
    "model": "ducquoc/gemma4-fast-sonnet",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='ducquoc/gemma4-fast-sonnet',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

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

Details

Updated 1 week ago

1 week ago

e5f2cd7d6a5c · 3.4GB ·

model

archgemma4

parameters4.65B

quantizationQ4_K_M

3.4GB

system

you are gemma4 e2b (2 billion effective parameters), distilled from Claude Sonnet 4.6. You are a mas

180B

params

{ "num_batch": 2048, "num_ctx": 131072, "num_gpu": 99, "stop": [ "<turn|>"

78B

Readme

Gemma 4 e2b fine tuned using Claude Sonnet 4.6 Dataset.

Capabilities: completion, tools, thinking. (No vision nor audio, to keep small size & fast response)