Alternatives
Products that do what I beat IBM's error rate by 30x using a 10-qubit Consensus Council does
- 1II
2019 · ericu.github.io
- 2LI
2011 · blog.self.li
- 3AR
2021 · guillaume.baierouge.fr
- 4IB
2021 · ronaldlangeveld.com
- 5IB
2018 · peerdium.com
- 6A1
2014 · github.com
- 7IW
2019 · enigma.lh.mk
- 8IB
Jun 2026 · github.com
- 9IB
2021 · github.com
- 10BA
2020 · andrewsun.com
- 11IB
2019 · tillypay.com
- 12II
2024 · medium.com
- 13MS
2011 · github.com
- 14IB
2021 · danhough.com
- 15IB
Dec 2025 · friggeri.net
- 16AF
Oct 2025 · qblaze.org
- 17IB
2024 · github.com
- 18SP
Jul 2026 · silicon.bergkv.ist
- 19IB
May 2026 · github.com
- 20AT
2013 · dl.dropboxusercontent.com
- 21HA
2018 · github.com
- 22IR
Democratisation of local AI is key. I've been working on pushing the limits of commercial hardware, squeezing any extra bit possible. My Scientific Agentic AI hareness helped me to reallocate every single bit of it. I rewrote the Kernel, I went down the CUDA rabbit hole until I have been able to explain any bit and any ms of computational power involved in the process pushing the Qwen 30B-A3B from 8 tok7s to 19 tok/s with llama.cpp up to 22.2 tok/s with my project and 109 tok/s on not novel content and speeding up the prefill by 5-9X
Jul 2026 · github.com
- 23IB
2024 · omniplex.ai
- 24PC
2014 · particle-clicker.web.cern.ch
Ranked by how close each launch is in meaning, then by votes. Refine with a description →