What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- Whether using the engine still makes sense when there is enough memory to hold the whole model.From this comment
- Why the measured speeds vary so widely between different machines and storage.From this comment
- How often the chosen experts actually change per token and how long runs of repeats last.From this comment
- Whether continuous weight streaming could damage the drive or overheat a fanless laptop.From this comment
- How the approach compares with plain memory mapping that existing local runtimes already use.From this comment
What they doubted or pushed back on our summary
- Sustained reads and long batch runs could wear the storage or cause early thermal throttling.From this comment
- The engine only works on one platform, so users elsewhere are left without an option.From this comment
- Requiring a newer system version makes compiling harder on older machines.From this comment
- The base model is weak for coding, so people want support for other model families.From this comment
What the maker answered our summary
64 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- On the same model and context, the engine used far less memory but ran at roughly half the speed.From this comment
- The speed gap came from faster reads and graphics work, with caching helping even inside the memory limit.From this comment
- Full expert selection changes nearly every token, but partial reuse nearly halves the reads.From this comment
- Switching from mapped reads to parallel reads gave the largest gain, from about half a token to four per second.From this comment
What a builder can take from it: Experiment on the target hardware and measure before assuming a memory-saving trick will be fast enough. our reading
The title, taken apart our calculation
This post got 919 points; the median for all 1442 posts is 112. In Open source projects (328 posts) the median is 103 points and 38 comments.
When it was posted our calculation
Wednesday at 15:00 UTC. Of 4,000 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 133 (3.3%) reached 50 points; on Wednesdays it was 2.6% of 8,118. The average over all hours is 2.9%. One post's time does not explain its result; the full table of hours is on the Show HN hub.
Check your title our calculation
Type the title you plan to post. It is compared with 1,442 Show HN posts that reached 50 or more points: its length, its shape, and how posts of that length and shape did. Nothing is sent anywhere.
Type a title above to see where it sits.
Draft my Show HN post
Paste your site address and get title options and a first comment for your own Show HN post, written from what your site says and checked against the numbers above. Nothing is posted for you.
Free to try and no account needed. FoxPlug is for people who ship several projects and keep stalling on telling anyone: it turns what you ship into posts you approve before anything goes out. See what each plan includes.
More Open source projects teardowns
Points, comments, titles and times are Hacker News's own numbers, read from the post itself, last updated Nov 2026. Summaries of what people said are ours, written in our own words, and each one links to the comment it came from. Percentages and medians marked "our calculation" are computed from the posts counted on the page: they describe what happened, not what will happen to your post. FoxPlug posts nothing for you. Plans and limits are on the pricing page. Questions: support.
After the launch post: a changelog your users read
A launch brings visitors once. FoxPlug turns what you ship afterwards into a public changelog and ready posts, so the next visitor finds something new.
Start your changelog See a SaaS changelog example
Free to start. Pro is a month.
FoxPlug Pro
- A public changelog page and feed for each project
- Visual cards and walkthrough videos made from what you shipped
- Posts for X, LinkedIn and dev.to written from your changes
- Connect GitHub and the tools you build with