[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)

Details

Updated 3 months ago

3 months ago

154036c227fe · 6.6GB ·

model

archqwen35

parameters9.65B

quantizationQ4_K_M

6.6GB

license

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

template

{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|> {{- else if .M

1.7kB

system

You are Qwen, created by Alibaba Cloud. You are a helpful assistant.

68B

params

{ "num_predict": -1, "presence_penalty": 1.5, "repeat_penalty": 1.1, "temperature":

104B

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.