Omoeba/qwen3-2507-thinking-128k

Omoeba/ qwen3-2507-thinking-128k

44 Downloads Updated 1 year ago

qwen3-2507 with thinking enabled and a default context length of 128k

tools thinking 30b

ollama run Omoeba/qwen3-2507-thinking-128k:30b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "Omoeba/qwen3-2507-thinking-128k:30b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='Omoeba/qwen3-2507-thinking-128k:30b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'Omoeba/qwen3-2507-thinking-128k:30b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)