I Benchmarked Local LLMs on the Laptop I Have

konmam1 pts0 comments

I Benchmarked Local LLMs on the Laptop I Already Have :: mamonas.devm.

mamonas.devAug 10, 2026tech8 min read<br>I Benchmarked Local LLMs on the Laptop I Already Have<br>My last post was about companies discovering their AI bills and installing caps. A reasonable reaction to that post is the one the local-LLM crowd has been giving all year: stop renting tokens, the open models are good now, just run them on your own machine.<br>The benchmarks backing that advice have a hardware problem. The writeups that measure anything run on Mac Studios or 128GB M5 Max laptops, and the headline stories are worse. DeepSeek V4 Flash &ldquo;runs on a MacBook&rdquo; if the MacBook is a 128GB build that costs about $5,000. Kimi K3 has open weights that need eight H100s just to load. One guide this summer was literally titled &ldquo;Open Weights You Can&rsquo;t Run.&rdquo;<br>My laptop is a 2021 M1 Pro with 16GB of RAM. It&rsquo;s almost five years old, and I suspect it&rsquo;s a lot closer to the median developer machine than anything in those benchmarks. So I benchmarked what it can actually do.<br>The Setup⌗<br>I tested five models, all pulled through Ollama, all picked to fit in 16GB:<br>qwen3.5:4b and qwen3.5:9b , Alibaba&rsquo;s current small models, both of which think before answering by default<br>gemma4:e4b-it-qat and gemma4:12b-it-qat , Google&rsquo;s current small family, in the quantization-aware builds<br>qwen2.5:7b , a late-2024 model, as the baseline for whether a year of progress shows up at this size<br>The current models everyone actually talks about didn&rsquo;t make the list, and that&rsquo;s a finding on its own. glm-4.7-flash and qwen3-coder both sound small and both are 19GB downloads. Qwen3.8-27B, announced the week I ran this, needs about 17GB and its weights weren&rsquo;t even downloadable yet, they&rsquo;re promised for the week this post goes out. On 16GB of RAM the list of models you can actually run is much shorter than online discussions suggest.<br>The tasks are 21 problems of the kind that come up in a data engineer&rsquo;s week, in six categories: writing DuckDB SQL against a seeded database, fixing buggy Python files with a failing test suite, extracting JSON from messy text like Airflow logs and billing emails, predicting what tricky Python snippets print, answering quick questions I&rsquo;d normally google, and finding facts planted in a 7,400-token runbook. Everything is graded by code, not by me reading the answers: generated SQL gets executed and compared row by row against a reference query, bug fixes have to pass pytest, extractions are checked field by field. Each model also has a temperature setting that controls how much randomness goes into its answers, I set it to zero and ran everything twice, so each model gets 42 runs.<br>What Passed⌗<br>modelsizepass ratetotal wall timegemma4:12b-it-qat7.2GB38/42 (90%)123 mingemma4:e4b-it-qat6.1GB36/42 (86%)18 minqwen3.5:9b6.6GB34/42 (81%)114 minqwen3.5:4b3.4GB26/42 (62%)125 minqwen2.5:7b4.7GB22/42 (52%)3 minTwo things surprised me here. The first is how much these models get right. Gemma 4&rsquo;s 12B answered 90% of the suite correctly, including 6/6 bug fixes that had to pass an actual test suite and 8/10 SQL questions graded by execution. The 2024 baseline managed 52% on the same tasks and went 0 for 6 on predicting what Python code prints, so the models did improve over the year, at least between those two.<br>The second surprise is the wall-time column. The old qwen2.5 ripped through the whole suite in 3 minutes. The models that beat it needed one to two hours for the same 42 runs, and almost all of that gap is reasoning tokens.<br>% passed50607080900306090120qwen2.5:7bgemma4:e4bqwen3.5:9bgemma4:12bqwen3.5:4bwall-clock minutes for the full 42-run suiteAccuracy against time for the whole suite. Only gemma4:e4b is both fast and accurate.The Reasoning Tax⌗<br>The current generation thinks before answering, and on a laptop that thinking is where most of the time goes.<br>My first run capped generation at 3,072 tokens per task, which is not much considering how many tokens something like Claude uses on a single request. The qwen3.5 models hit that cap in 48 out of 84 runs, spending the entire budget on reasoning and never producing an answer. Both scored around 40-57%. I doubled the budget to 8,192 and reran: both gained exactly ten passes. The ability was there, the models just needed thousands of extra tokens to reach the answer. Some runs blew through the doubled budget too. qwen3.5:9b spent eight minutes and 34,000 characters of thinking on one SQL question and still ran out of room.<br>The gemma models think too, usually less, but not always. On one run, gemma4:12b spent 14 minutes reasoning about which numeric chmod mode corresponds to rwxr-xr–, produced 19,000 characters of thinking, and answered 750. The answer is 754.<br>On the API this same behavior shows up as a line item, the reasoning tokens get billed like any others. Locally it shows up as time spent waiting.<br>Would You Stop Googling...

rsquo models tokens qwen3 laptop runs

Related Articles