What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- Which inference libraries and versions are used for each model's speed measurement?From this comment
- Can the tool account for how well a system handles parallel prefill for agentic coding?From this comment
- How closely do these simulated results match real-world usage for a database query workflow?From this comment
- Will support be added for multi-GPU setups, PCIe generations, NVLink, and bifurcation?From this comment
- Could users set a custom tokens-per-second value instead of relying on hardware options?From this comment
What they doubted or pushed back on our summary
- The reported speed for one high-end machine is nearly half what a user measures on similar hardware.From this comment
- Older budget cards like the RX580 that still run models well are excluded.From this comment
- Hybrid combinations such as two different graphics cards are not supported.From this comment
- The estimates use minimal token counts and ignore optimized methods like speculative decoding or context size.From this comment
What the maker answered our summary
5 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- The maker will explore adding harness details but notes benchmark sources often lack that data.From this comment
- The maker asked which model and quantization a commenter tested to investigate the speed discrepancy.From this comment
- The maker announced that new model and hardware benchmarks are now live.From this comment
What a builder can take from it: A speed simulator for hardware buyers must be transparent about its measurement conditions, support common setups, and respond quickly to accuracy complaints. our reading
The title, taken apart our calculation
This post got 331 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
Saturday at 04:00 UTC. Of 1,003 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 30 (3%) reached 50 points; on Saturdays it was 3% of 4,953. 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