doomgrave/qwen3

doomgrave/ qwen3

341 Downloads Updated 1 year ago

qwen3, quantized to Q2_K and Q3_K_S for GPU with 4gb Vram or less.Edit

tools

ollama run doomgrave/qwen3:1.7b-Q3_K_S

curl http://localhost:11434/api/chat \
  -d '{
    "model": "doomgrave/qwen3:1.7b-Q3_K_S",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='doomgrave/qwen3:1.7b-Q3_K_S',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'doomgrave/qwen3:1.7b-Q3_K_S',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)