pielee/qwen3-4b-thinking-2507

pielee/ qwen3-4b-thinking-2507_q8

1,352 Downloads Updated 1 year ago

Qwen3-4B-Thinking-2507_q8: A 4-billion-parameter inference model with 8-bit quantization, optimized for efficient reasoning in resource-constrained environments.

tools thinking

ollama run pielee/qwen3-4b-thinking-2507_q8

curl http://localhost:11434/api/chat \
  -d '{
    "model": "pielee/qwen3-4b-thinking-2507_q8",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='pielee/qwen3-4b-thinking-2507_q8',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'pielee/qwen3-4b-thinking-2507_q8',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)