radenadri/Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

radenadri/ Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

1,746 Downloads Updated 3 months ago

A lightweight but surprisingly capable reasoning model — distilled from Claude 4.6 Opus, quantized to Q4_K_M for local use.

ollama run radenadri/Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

curl http://localhost:11434/api/chat \
  -d '{
    "model": "radenadri/Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-GGUF",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='radenadri/Qwen3.5-0.8B-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: 'radenadri/Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-GGUF',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

1 model

Size / Usage

Context

Input

Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-GGUF:latest

527MB · 256K context window · Text · 3 months ago

Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-GGUF:latest

527MB

256K

Text

Readme

This is a GGUF quantization of Qwen3.5-0.8B, enhanced through Chain-of-Thought (CoT) distillation from Claude-4.6 Opus. It is designed to deliver superior reasoning capabilities in a compact, ultra-efficient 0.8B parameter package.

https://huggingface.co/Jackrong/Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-GGUF