24 2 weeks ago

Qwen with Thinking

vision tools thinking 0.6b 0.8b 1.2b
ollama run neolinschen/Qwen-Thinking:1.2b

Details

2 weeks ago

f2612f5c2d3d · 731MB ·

lfm2
·
1.17B
·
Q4_K_M
LICENSE TEXT LFM Open License v1.0 TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. D
You are Qwen. Think hard, provide a clear, well-structured answer for the user. Answer in the user's
{ "temperature": 0.05, "top_k": 50 }

Readme

Gemma Coding 🤖

A lightweight coding assistant based on Google’s Gemma 3, optimized for coding tasks and agent workflows.

Models

Tag Size Best for
270m ~200MB Fast, low resources
1b ~800MB Balanced
4b ~3GB Best quality

Usage

ollama run neolinschen/Gemma-Coding:4b

What it can do

  • Write and debug code in any language
  • Explain code step by step
  • Help with agent tasks and automation
  • Answer coding questions concisely

Based on

Gemma 3 by Google