Alternatives
Products that do what MiniPCs.zip – Charting the Pareto frontier of Mini PCs does
The overall idea is to chart out the thousands of Mini PCs by benchmark and reveal the Pareto Front so you can get the most Compute per Dollar. Definitely a labor of love as I have a number of Mini PCs for my "homelab" (TrueNAS, piHole, Plex, basic stuff). It uses Gemini to extract specs from listings (since they're not often strongly categorized). Quick blog post here: https://luke.zip/posts/pareto-pcs/
- 1PI
Hi HN! I’m Alex from Parabola (https://parabola.io). Parabola is a visual programming tool for creating functional data flows that everyone can use. It’s entirely drag-and-drop, handles data sizes much larger than a traditional spreadsheet, calculates everything live, and can run your flows on a schedule of your choosing. I used to work in strategy consulting, doing data analytics for SMBs and Fortune 500 companies. The amount of time wasted on menial tasks was astounding. Things like cleaning data, generating custom reports, creating human workflows to solve shortcomings in third…
2018 · parabola.io
- 2
- 3MH
May 2026 · stocks.sjer.red
- 4IM
Hello everyone. I'm a relatively new developer and I started my first project to go full production recently. It is a directory of payment processors and payment service providers. It's free to use and gives detailed info on their pricing, business model, supported business types, available countries, prohibited businesses and high risk business support. So far only 40 have been added with more to come. And I allow processors to contact me so that they're details can be added to the database. I'll eventually automate this and add verification the months to come. I hope you'll find it useful.…
2025 · sourcefees.com
- 5RG
I wanted to know how fast a 26B mixture-of-experts model could run on a desktop CPU with no GPU. Got ~40 tok/s single-stream (lossless) and ~124 batched. The surprising part was the byte budget: for this model you compress the output head (32% of per-token bytes), not the experts (16%). The writeup has the bandwidth roofline and the dead-ends; the repo has the reproducible recipe. Happy to answer questions. Repo: https://github.com/arun-prasath2005/gemma4-cpu-moe
Jun 2026 · apeg.dev
- 6IP
See https://github.com/rodgarrison/rdpmc If you've been interested in micro-benchmarking code using Intel's PMU HW capability to capture per HW core metrics, this repository may be for you. The repository includes 'doc/pmu.md' with a copy of Intel's software reference manuals (PDF) so, all in one place, you can understand and develop PMU profiling for your Intel micro architecture. Example included. Source code is 451 LOC with comments. Features: * Minimum, complete * Does not require yum install msr-tools * Header only: include and you're done * Works in user-space…
2022
- 7
I made this after seeing someone posit the idea online yesterday over lunch then spent some time refining it. So far it's pretty impressive IMO! Right now I am running Qwen3-30B-A3B on my 24gb unified memory m4 MacBook Pro at 50 tok/sec and this should definitely not be working for such a large model on my middling hardware. Things are detailed in the README to get up and running and DESIGN.md has details on all the choices and such made along the way.
23d ago · github.com
- 8
- 9AG
We built, saga[1] a layer that lets smaller teams access enterprise GPU discounts through collective buying power. How it works: 1. Aggregate GPU spend across hundreds of ML teams 2. Get enterprise rates through combined volume 3. Pass savings to users, monetize via provider partnerships Technical notes: - Works at billing layer only (no access to code/data) - Supports existing cloud setups or managed GPUs - Private beta running since January, opening more spots for March - Currently seeing ~50% savings on H100s/A100s [1] https://trysaga.ai
2025 · trysaga.ai
- 10IM
I spent last 6 months trying to build Simple Ops [1] to democratize website performance monitoring so anyone can use it. A year back, while I was trying to measure performance for Visa List as it became a huge content website with more than 100K pages. Also as data is changing very frequently, it's very hard to keep doing this manually. I searched on google and found that all the solutions are just uptime monitoring and nothing and none of them truly measure performance. So I decided to build one for myself. But it turns out website performance monitoring is not so simple after all and with…
2020
- 11RS
Hi HN! I've been hacking on this side project for the last month or two with the goal of making it dead simple to use cloud GPUs. I ran into this problem personally during the phd, and built my own tooling around it. I always thought it'd be fun to try to turn that tooling into a more general product... and bitbop.io is the result! All you have to do is run `ssh bitbop.io`, and you get your own personal dev GPU workstation in the cloud. Looking forward to hearing your thoughts!
2024 · twitter.com
- 12IB
Built a simple web app that tells you which open-source LLMs will work on your hardware. It auto-detects your specs, shows compatible models from Hugging Face, gives realistic performance estimates (tokens/sec), and recommends quantization settings. You can also manually input specs to see "what if I upgraded my RAM?" Made this after wasting time downloading giant models only to find they crawled on my hardware. Hope it saves you some frustration!
2025 · caniusellm.com
- 13IB
I built a web page that aggregates data about data center buildup, sovereign fund investments into AI and bottlenecks. The objective is to predict AI race cooldown by looking at a potential decrease of activity involving these elements. The website looks at the quarterly forms from the 5 biggest hyperscalers and adds their CapEx into the mix, calculating a composite index in the end showing how likely it is for the AI race to slow down. Enjoy!
Jul 2026 · laurentiugabriel.github.io
- 14VE
A bit late in the new diskprices-like website trend, but here's my contribution to the ecosystem. The goal here is to get an instant comparison of the laptops on ebay, using mostly 3 metrics of now: CPU benchmark rank, GPU benchmark rank, and price, without having to scroll through the item description or google the PC model. At the moment there are some parsing bugs, and some components that aren't parsed yet. I also quickly run into the ebay rate limit, making it hard to maintain an hour-by-hour listing. Curious to know what you guys think!
2024 · laptopscout.xyz
- 15GP
Out of curiosity, I put together a simple website which tracks the prices for a few variations of A100/H100 GPUs by hour broken out between spot/ondemand, form factor and provider. Specifically I was tailoring the tool towards the smaller, emerging providers like runpod, gpulist.ai, lambda labs etc. Anyone have any ideas to expand/refine it?
2024 · computeindex.michaelgiba.com
- 16IB
I was overspending on GPT-4o. It was really hard to compare different models I could switch to, so I built this LLM comparison tool. It shows leaderboards, pricing, and performance data across 100+ LLMs (including all major providers and open-source models). Key features: - Live pricing comparisons - Benchmark Scores (MMLU, HumanEval, GPQA, etc.) - Context length vs cost analysis - Speed/throughput tests across providers - Quality vs price visualizations - Open source (all data verifiable) Try it out: https://llmstats.com I'd like to know your opinion :) Tech stack: Next.js,…
2025 · llm-stats.com
- 17UI
We built this database using the same software investors use to discover startups. My friends and I really wanted to know which startups to work for. Are we on the right track? PS - there's a paywall but if you want to explore more, just DM me your email and I'll send you a free access code! Thank you so much.
2023 · usemassive.com
- 18WM
Hi HN, I’ve spent the last decade building hardware products like humanoid robots, 3D printers, and self-driving tractors. I needed a tool to navigate technical documents faster, so I created one with friends. This tool helps with component search, cross-referencing, comparison, and debugging. We’d love your feedback, whether you find it useful or not. Thank you! Try it here: www.convergelab.ai
2024 · convergelab.ai
- 19IM
I build a lot of small products myself and I realized how many indie founders want an exit that doesn’t involve platforms charging large commissions or requiring big revenue numbers. Sometimes a project makes $50/month, sometimes $500, sometimes $0 but has a great codebase, and that’s enough value for someone else. So I built buy-startups.com, a very simple, privacy-friendly marketplace for buying and selling small online startups. It’s not fancy. There’s no commission, no listing fee, no hidden funnel. Just a straightforward way for indie devs and bootstrappers to list a project and…
Dec 2025 · buy-startups.com
- 20BA
Hey HN! I work on a database for my day-job and I realized I had never written one from scratch, so I wrote bugfruit! Once I was mostly satisfied with it, I looked up some benchmarks to compare my simple database to other brand name key-value stores. I was surprised to see that mine held up fairly well on the subset of benchmarks I replicated. So I used the Pavlo Database Naming System [0] to name it and open-sourced the code. I'd love to hear any feedback you might have on it! [0] https://www.cs.cmu.edu/~pavlo/blog/2020/03/on-naming-a-datab...
2022 · github.com
- 21GF
I've been a big fan of fly.io with it’s devx, but cold starts and pricing have been a consistent problem. Even for side projects it's painful if they take 30s to load, it just kills the whole experience. With coding agents becoming good, there were a lot more things I started building, and I just wanted to run all of those things! GCI was built to solve this. It’s just a CLI, just uses ssh to interact with your target machine, and relies on docker swarm to get your services running (docker swarm is IMO underrated, providing benefits even with a single node). It can deploy on any machine that…
Mar 2026 · github.com
- 22AN
Kimi K3 has 2.78 trillion parameters and ships as 1.42 TB of weights. It clearly does not fit in the memory of a laptop. But K3 is a Mixture-of-Experts model. For each token, only a small fraction of its 896 experts per layer is activated. That changes the problem: the entire model does not need to be resident in RAM, as long as the weights required by each token can be reached quickly enough. We built WASTE — the Weight-Aware Streaming Tensor Engine — to explore that idea. WASTE keeps the dense, repeatedly used part of the model resident in memory, stores the routed experts in an…
Jul 2026
- 23IM
I made my first macOS utility app that ships with a bundled Gemma 4 model, specifically the Gemma E4B one. It made my app DMG have 5.3 GB in size, but I think it is a small size for the power that this free local model can provide. It runs fine on CPU, but can also run on Apple Silicon GPU, although I did not notice any performance improvements with GPU (tested on a M5 chip). I think these local lightweight and multimodal models will open multiple possibilities for new software tools where privacy is essential.
May 2026 · snapname.app
- 24ES
Hi HN, I built EdgeVec, a vector database that runs entirely in the browser. It implements HNSW (Hierarchical Navigable Small World) graphs for approximate nearest neighbor search. Performance: - Sub-millisecond search at 100k vectors (768 dimensions, k=10) - 148 KB gzipped bundle - 3.6x memory reduction with scalar quantization Use cases: browser extensions with semantic search, local-first apps, privacy-preserving RAG. Technical: Written in Rust, compiled to WASM. Uses AVX2 SIMD on native, simd128 on WASM. IndexedDB for browser persistence. npm:…
Dec 2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →