https://dschloe.github.io/categories/llm/Recent content in LLM on Data Science | DSChloeHugoen-USWed, 19 Aug 2026 21:30:00 +0900https://dschloe.github.io/programming/2026/08/ollama-advisor/Wed, 19 Aug 2026 21:30:00 +0900https://dschloe.github.io/programming/2026/08/ollama-advisor/<h2 id="개요">개요</h2> <p><a href="https://github.com/dschloe/ollama-advisor">ollama-advisor</a>는 시스템 사양(RAM, GPU VRAM)과 사용 목적(코딩, 추론, 비전, 임베딩 등)에 따라 실행 가능한 <a href="https://ollama.com">Ollama</a> 모델을 자동으로 추천해주는 Python 라이브러리입니다.</p> <p>Mac, Windows, Linux, Google Colab 모두 지원합니다.</p> <ul> <li><strong>PyPI</strong>: <a href="https://pypi.org/project/ollama-advisor/">ollama-advisor</a></li> <li><strong>GitHub</strong>: <a href="https://github.com/dschloe/ollama-advisor">dschloe/ollama-advisor</a></li> </ul> <h2 id="설치">설치</h2> <div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;-webkit-text-size-adjust:none;"><code class="language-bash" data-lang="bash"><span style="display:flex;"><span>pip install ollama-advisor </span></span></code></pre></div><h2 id="사용법">사용법</h2> <h3 id="시스템-사양-확인">시스템 사양 확인</h3> <p>Ollama가 설치되어 있지 않아도 시스템 사양을 확인할 수 있습니다.</p> <div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;-webkit-text-size-adjust:none;"><code class="language-python" data-lang="python"><span style="display:flex;"><span><span style="color:#f92672">import</span> ollama_advisor <span style="color:#66d9ef">as</span> oa </span></span><span style="display:flex;"><span> </span></span><span style="display:flex;"><span>specs <span style="color:#f92672">=</span> oa<span style="color:#f92672">.</span>get_system_specs() </span></span><span style="display:flex;"><span><span style="color:#66d9ef">for</span> k, v <span style="color:#f92672">in</span> specs<span style="color:#f92672">.</span>items(): </span></span><span style="display:flex;"><span> print(<span style="color:#e6db74">f</span><span style="color:#e6db74">&#34;</span><span style="color:#e6db74">{</span>k<span style="color:#e6db74">}</span><span style="color:#e6db74">: </span><span style="color:#e6db74">{</span>v<span style="color:#e6db74">}</span><span style="color:#e6db74">&#34;</span>) </span></span></code></pre></div><div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;-webkit-text-size-adjust:none;"><code class="language-text" data-lang="text"><span style="display:flex;"><span>ram_gb: 16.0 </span></span><span style="display:flex;"><span>gpu: {&#39;type&#39;: &#39;apple&#39;, &#39;name&#39;: &#39;Apple Silicon (unified memory)&#39;, &#39;vram_gb&#39;: 16.0} </span></span><span style="display:flex;"><span>usable_gb: 12.8 </span></span><span style="display:flex;"><span>platform: mac </span></span></code></pre></div><p>Apple Silicon Mac (16GB)에서 실행한 결과입니다. 사용 가능한 메모리가 12.8GB(전체의 80%)로 계산됩니다.</p>