What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- Whether KV cache estimates handle sliding window attention models at long context.From this comment
- How this differs from an existing tool that checks whether a model fits.From this comment
- Support for additional quantization formats beyond what is currently listed.From this comment
- Maximum context length possible on top of the baseline, also asking for a web version.From this comment
- Whether the tool actually runs and benchmarks models on the local machine.From this comment
What they doubted or pushed back on our summary
- The install method was broken and the tool recommended several outdated model versions.From this comment
- Accurate memory estimation is hard and cannot be generic across all local models.From this comment
- Unified memory architectures were misdetected, showing reserved instead of total GPU memory.From this comment
- Install and run this unknown project on your computer.From this comment
What the maker answered our summary
3 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- The KV estimate uses per-model head config but assumes dense attention, overestimating for sliding-window models.From this comment
- The tool ranks fitting candidates using merged benchmarks rather than only checking whether a model fits.From this comment
- By design it estimates without running, so measured throughput on your exact setup beats its numbers.From this comment
What a builder can take from it: Builders should expect hardware detection and memory estimates to need per-model attention math plus real measured runs before users trust the rankings. our reading
The title, taken apart our calculation
This post got 283 points; the median for all 1442 posts is 112. In AI and agents (352 posts) the median is 108 points and 49 comments.
When it was posted our calculation
Friday at 09:00 UTC. Of 1,532 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 37 (2.4%) reached 50 points; on Fridays it was 2.7% of 6,422. 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 AI and agents 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