[qwen3.5:9b] optimized for code assistant

vision tools thinking

ollama run cmd_er/cody

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

from ollama import chat

response = chat(
    model='cmd_er/cody',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'cmd_er/cody',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model cmd_er/cody

OpenCode ollama launch opencode --model cmd_er/cody

Hermes Agent ollama launch hermes --model cmd_er/cody

OpenClaw ollama launch openclaw --model cmd_er/cody

Models

View all →

Name

1 model

Size / Usage

Context

Input

cody:latest

6.6GB · 256K context window · Text, Image · 3 months ago

cody:latest

6.6GB

256K

Text, Image

Readme

Cody

Edition 260604

Cody is a lightweight model wrapper implemented as an experimental configuration derived from a subset of the Qwen3.5:9b architecture. This system is designated strictly for educational and research applications at the student level. It should be classified as a scientific experiment rather than a commercial product or an official release.

❗Note

Cody is not affiliated with, endorsed by, or distributed as an official artifact of the original model provider.