Instinct is Continue's state-of-the-art open Next Edit model. Robustly fine-tuned from Qwen2.5-Coder-7B, Instinct intelligently predicts your next move to keep you in flow.

tools

ollama run nate/instinct

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

from ollama import chat

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

import ollama from 'ollama'

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

Applications

Claude Code ollama launch claude --model nate/instinct

Codex ollama launch codex --model nate/instinct

OpenCode ollama launch opencode --model nate/instinct

OpenClaw ollama launch openclaw --model nate/instinct

Models

View all →

Name

1 model

Size

Context

Input

instinct:latest

4.7GB · 32K context window · Text · 5 months ago

instinct:latest

4.7GB

32K

Text

Readme

Instinct, the State-of-the-Art Open Next Edit Model

Instinct is Continue’s state-of-the-art open Next Edit model. Robustly fine-tuned from Qwen2.5-Coder-7B on our dataset of real-world code edits, Instinct intelligently predicts your next move to keep you in flow.

Learn more

For more information on the work behind Instinct, please refer to our blog.