kwangsuklee/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

kwangsuklee/ Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF:latest

2,999 Downloads Updated 5 days ago

26.3.7. Qwen3.5-27B-Q4 Update: This model introduces higher-quality reasoning trajectories across domains such as science, instruction-following, and mathematics.

ollama run kwangsuklee/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

curl http://localhost:11434/api/chat \
  -d '{
    "model": "kwangsuklee/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='kwangsuklee/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'kwangsuklee/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 5 days ago

5 days ago

34012a1feb3c · 17GB ·

model

archqwen35

parameters26.9B

quantizationQ4_K_M

17GB

params

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

63B

Readme

Qwen3.5-27B-Q4.

This model aims to improve structured step-by-step reasoning and reasoning diversity. The model’s goal is to leverage state-of-the-art Chain-of-Thought (CoT) distillation primarily sourced from Claude-4.6 Opus interactions. This model introduces higher-quality reasoning trajectories across domains such as science, instruction-following, and mathematics.

https://huggingface.co/Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

Original Model :

https://ollama.com/library/qwen3.5:27b