MicroLLM Lab – Try 7 tiny LLM's in the browser

原始链接: https://stateofutopia.com/experiments/microllmlab/

该界面提供了一套强大的工具包，可直接在浏览器中对大语言模型 (LLM) 进行基准测试。 **主要功能：** * **自定义评估：** 用户可以编写基于 JavaScript 的基准测试，通过客观检查（正则表达式或精确标记匹配）而非主观质量分析来测试模型。 * **性能指标：** 该平台可测量准确性和速度，提供峰值速度、持续解码（256 个标记）以及总执行时间的数据。 * **隐私与便携性：** 所有基准测试数据均保存在本地。用户可以生成并下载性能证书、复制文本摘要，或将结果直接分享至 X 和 LinkedIn 等社交平台。 * **易用性：** 该系统包含根据以往每秒标记数预估性能、同时运行多个已加载模型的测试套件，以及提示大型 LLM 辅助编写新测试用例的工具。简而言之，该工具提供了一个私密的、以开发人员为中心的测试环境，无需依赖外部服务器即可评估和比较 LLM 的效率与功能表现。

Next action:

Objective checks (regex / exact tokens), not writing quality. A 135M model is allowed to fail — that is the measurement. Pick models, then run. Estimate uses your last tok/s if we have one.

🏎️ Highest Peak Speed — Fastest single test

⚡ Highest Sustained Speed — Continuous 256-tok decode

📊 Avg Sustained Speed — Across tested models

⏱️ Total Benchmark Score — Cumulative suite wall time

Next action:

Speed (tokens/s, sustained decode, suite wall) and accuracy (pass rate on objective tests) from runs in this browser. Numbers stay on this machine. Charts use the latest suite per model.

🏎️ Highest Peak Speed — Fastest single test

⚡ Highest Sustained Speed — Continuous 256-tok decode

📊 Avg Sustained Speed — Across loaded models

⏱️ Total Benchmark Score — Total execution wall time

Next action:

Write a benchmark in JavaScript

The editor is eval()’d in this origin, then each check runs on the model’s decoded text.

            <div class="callout">
              <h3>Prompt for a larger LLM</h3>
              <p><button class="btn" id="copy-llm">Copy prompt</button></p>
              <textarea id="llm-prompt" class="code" readonly="readonly"/>
            </div>
            

            <!-- Bottom navigation repeated at bottom of custom eval studio -->
            <p>
              <span class="bottom-nav-label">Next action:</span>
              <nav class="tabs bottom-tabs" role="tablist" aria-label="Custom eval bottom navigation">
                <button type="button" data-tab="chat">Chat</button>
                <button type="button" data-tab="bench">Benchmarks</button>
                <button type="button" data-tab="compare">Compare & Certificate</button>
                <button type="button" data-tab="studio" aria-selected="true">Custom eval</button>
              </nav>
            </p>
          </section>
        </div>        </div>
    </div>
</div>
<div class='clear'></div>    </div>
    <div style='position:fixed; bottom:0; left:0; right:0;'>
        </div>
    <div align='center' style='border-top:1px solid #EEE; padding:1em; margin-top:2em;'>
  联系我们 contact @ memedata.com
</div>
<!-- Global site tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-PFMR8YTWGP"></script>
<script>
  window.dataLayer = window.dataLayer || [];
  function gtag(){dataLayer.push(arguments);}
  gtag('js', new Date());

  gtag('config', 'G-PFMR8YTWGP');
</script>
</body>
</html>