voytas26/openclaw-qwen3vl-8b-opt

voytas26/ openclaw-qwen3vl-8b-opt

3,886 Downloads Updated 1 month ago

Optimized 8B (qwen3-vl:8b) for OpenClaw agents. Precise JSON tool calls, <thinking> reasoning, temp 0.5, 16k ctx. Runs smoothly on 8GB VRAM laptops with minimal hallucinations.

vision tools thinking

ollama run voytas26/openclaw-qwen3vl-8b-opt

curl http://localhost:11434/api/chat \
  -d '{
    "model": "voytas26/openclaw-qwen3vl-8b-opt",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='voytas26/openclaw-qwen3vl-8b-opt',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'voytas26/openclaw-qwen3vl-8b-opt',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)