DedeProGames/open-reasoner2

DedeProGames/ open-reasoner2

23 Downloads Updated 2 days ago

OpenReasoner is a fine-tuned model from the Qwen3.5 family, trained on three reasoning datasets.

vision tools thinking 0.8b 9b

ollama run DedeProGames/open-reasoner2:0.8b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "DedeProGames/open-reasoner2:0.8b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='DedeProGames/open-reasoner2:0.8b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'DedeProGames/open-reasoner2:0.8b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model DedeProGames/open-reasoner2:0.8b

Codex ollama launch codex --model DedeProGames/open-reasoner2:0.8b

OpenCode ollama launch opencode --model DedeProGames/open-reasoner2:0.8b

OpenClaw ollama launch openclaw --model DedeProGames/open-reasoner2:0.8b

Models

View all →

Name

2 models

Size

Context

Input

open-reasoner2:0.8b

1.0GB · 256K context window · Text, Image · 2 days ago

open-reasoner2:0.8b

1.0GB

256K

Text, Image

open-reasoner2:9b

6.6GB · 256K context window · Text, Image · 2 days ago

open-reasoner2:9b

6.6GB

256K

Text, Image

Readme

OpenReasoner is a fine-tuned model from the Qwen3.5 family, trained on three reasoning datasets open-thoughts/OpenThoughts3-1.2M, nvidia/OpenCodeReasoning-2, and nvidia/OpenMathReasoning—optimized for strong reasoning performance while remaining highly efficient for its size.