kwangsuklee/Qwen3.5-4B.Q4_K_M-Claude-4.6-Opus-Reasoning-Distilled-v2

kwangsuklee/ Qwen3.5-4B.Q4_K_M-Claude-4.6-Opus-Reasoning-Distilled-v2:latest

504 Downloads Updated 1 week ago

26.3.18. Ver.2 update: This iteration is powered by 14,000+ premium Claude 4.6 Opus-style general reasoning samples, with a major focus on achieving massive gains in reasoning efficiency while actively improving peak accuracy.

ollama run kwangsuklee/Qwen3.5-4B.Q4_K_M-Claude-4.6-Opus-Reasoning-Distilled-v2

curl http://localhost:11434/api/chat \
  -d '{
    "model": "kwangsuklee/Qwen3.5-4B.Q4_K_M-Claude-4.6-Opus-Reasoning-Distilled-v2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='kwangsuklee/Qwen3.5-4B.Q4_K_M-Claude-4.6-Opus-Reasoning-Distilled-v2',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'kwangsuklee/Qwen3.5-4B.Q4_K_M-Claude-4.6-Opus-Reasoning-Distilled-v2',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 week ago

1 week ago

f8a99257bb2a · 2.7GB ·

model

archqwen35

parameters4.21B

quantizationQ4_K_M

2.7GB

params

{ "presence_penalty": 1, "temperature": 1, "top_k": 20, "top_p": 0.95 }

63B

Readme

Qwen3.5-4B.Q4_K_M-Claude-4.6-Opus-Reasoning-Distilled-v2

2026.3.18. Ver.2 update. Benchmark Results : Ver.1 > Ver.2.

https://huggingface.co/Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF

2026.3.7. Ver.1 update.

https://ollama.com/kwangsuklee/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

2026.3.2. Original Model :

https://ollama.com/library/qwen3.5:4b