Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507

tools

ollama run kamekichi128/qwen3-4b-instruct-2507

curl http://localhost:11434/api/chat \
  -d '{
    "model": "kamekichi128/qwen3-4b-instruct-2507",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='kamekichi128/qwen3-4b-instruct-2507',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'kamekichi128/qwen3-4b-instruct-2507',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 3 months ago

3 months ago

a6c0056919a7 · 2.5GB ·

model

archqwen3

parameters4.02B

quantizationQ4_K_M

2.5GB

template

{{- $lastUserIdx := -1 -}} {{- range $idx, $msg := .Messages -}} {{- if eq $msg.Role "user" }}{{ $la

1.4kB

params

{ "repeat_penalty": 1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }

62B

Readme

Qwen3-4B-Instruct-2507

Lightweight and powerful model by Qwen team

Model Overview

Item	Description
Base Model	Qwen3-4B-Instruct-2507
Quantized By	Unsloth
Format	GGUF (Q4_K_M)

Acknowledgements

Qwen Team for creating the base model
Unsloth for providing the quantization tools

License

This model is distributed under Apache 2.0 License.