Dev tools · alternatives · 2026
24 alternatives to Zero-power photonic language model–code
The model uses a 1024-dimensional complex Hilbert space with 32 layers of programmable Mach–Zehnder meshes (Reck architecture) and derives token probabilities directly via the Born rule. Despite using only unitary operations and no attention mechanism, a 1024×32 model achieves coherent TinyStories generation after < 1.8 hours of training on a single consumer GPU. This is Part 1 - the next step is physical implementation with $50 of optics from AliExpress.
Zero-power photonic language model–code is a language model that uses a 1024-dimensional complex Hilbert space with programmable Mach–Zehnder interferometer layers instead of traditional neural network components. It… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.
- 1
Bitmap & tilemap generation from a single example with the help of ideas from quantum mechanics - mxgmn/WaveFunctionCollapse
2016 · github.com · its alternatives →
- 2
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
Apr 2026 · github.com · its alternatives →
- 3
How small can a language model be while still doing something useful? I wanted to find out, and had some spare time over the holidays. Z80-μLM is a character-level language model with 2-bit quantized weights ({-2,-1,0,+1}) that runs on a Z80 with 64KB RAM. The entire thing: inference, weights, chat UI, it all fits in a 40KB .COM file that you can run in a CP/M emulator and hopefully even real hardware! It won't write your emails, but it can be trained to play a stripped down version of 20 Questions, and is sometimes able to maintain the illusion of having simple but terse conversations…
Dec 2025 · github.com · its alternatives →
- 4AT
A 3.16M-parameter INT4 transformer running entirely in the on-chip memory of a Xilinx Kria KV260. Zero DRAM in the token loop, 59,965 tok/s on the fabric, bit-exact. Chat with it live.
Aug 2026 · mikeayles.com · its alternatives →
- 5
filippo.io/mlkem768 is a pure-Go implementation of the post-quantum key exchange mechanism ML-KEM-768 optimized for correctness and readability.
2024 · words.filippo.io · its alternatives →
- 6
Zero-Knowledge Proofs (ZKPs) let an untrusted proved show that computation was executed correctly without revealing the inputs to the verifier. However to prove anything, the computation first has to be expressed as a circuit: a system of polynomial equations (constraints) over a finite field. Circuits are the assembly language of zk and every constraint costs prover (and sometimes verifier) time, so production circuits are aggressively hand-optimized. Over the last months, we have been experimenting with writing formal specifications instead and letting LLMs produce the circuits: as long as…
Jul 2026 · zk.golf · its alternatives →
- 7
Netmind Power▲272Hi HN, We just opened public access to Qwen3‑Coder‑480B‑A35B‑Instruct via a REST/SDK API. Why it might be interesting: - Fully open-source (Apache‑2.0): https://github.com/QwenLM/Qwen3-Coder - 480B params (35B active MoE), long context up to 1M tokens with YaRN - Matches Claude Sonnet/GPT‑4o on SWE-Bench Verified (81.6%) - Free tier: 100K tokens/month
2023 · netmind.ai · its alternatives →
- 8
- 9
Announcing GPT-4.1, GPT-4.1 mini, & GPT-4.1 nano in the API
2025 · openai.com · its alternatives →
- 10
Fast and efficient models optimized for coding and subagents
Mar 2026 · openai.com · its alternatives →
- 11
Zero▲134Vercel's programming language built for AI agents
Aug 2026 · zerolang.ai · its alternatives →
- 12
Qwen3.6-35B-A3B▲124The open sparse MoE model for agentic coding
Apr 2026 · qwen.ai · its alternatives →
- 13IB
We wanted to do something very challenging to prove to ourselves that we can do anything we put our mind to. The reasoning for why we chose to build a toy TPU specifically is fairly simple: - Building a chip for ML workloads seemed cool - There was no well-documented open source repo for an ML accelerator that performed both inference and training None of us have real professional experience in hardware design, which, in a way, made the TPU even more appealing since we weren't able to estimate exactly how difficult it would be. As we worked on the initial stages of this project, we…
2025 · tinytpu.com · its alternatives →
- 14AQ
2019 · qml.entropicalabs.io · its alternatives →
- 15
Python client SDK for the Qumulator quantum computing API - qumulator/qumulator-sdk
Apr 2026 · github.com · its alternatives →
- 16
- 17
It is based on phase noise, consumes less than 60 LUT4s/FFs and achieves up to 7.99 bits of entropy per byte. Feel free to comment if you have any questions, ideas or thoughts :)
2023 · github.com · its alternatives →
- 18
Hi! I built this to teach myself how a quantum circuit simulator works. It's about 1000 lines of Python, aiming to be understandable more than being fast or robust. It's not meant to compete with anything else - just a personal project to really get clear on the under-the-hood theory of qubits and quantum gates.
2024 · github.com · its alternatives →
- 19
Hi HN, I turned the freshly published paper “The Constructor Theory of Time” by David Deutsch and Chiara Marletto (arXiv, 13 May 2025) into an executable Python library. What you’ll find • One-to-one translation of the paper’s formalism: Substrates, Attributes, Tasks, Constructors, and task-algebra operators • Possibility / impossibility predicates and counterfactuals encoded exactly as defined • Test suite that mirrors every lemma and example (>95 % coverage, mypy-typed) • Reproductions of key results: time-keeping substrates, irreversibility proofs, quantum branching tasks, and a…
2025 · github.com · its alternatives →
- 20RX
Hi all, long time lurker, first time poster. I want to share with you all something we've been working on for a while at Lambda: the Razer x Lambda Tensorbook: https://www.youtube.com/watch?v=wMh6Dhq7P_Q But before I tell you about it, I want to make this all about me, because I built this for me. See, while I'm genuinely interested in hearing from the community what you think as this is the culmination of a lot of effort from a lot of people across so many different fields (seriously, the number of folks across manufacturing, engineering, design, logistics, and marketing who…
2022 · its alternatives →
- 21
Haskell re-implementation of STOKE, the stochastic superoptimizer - blaze/notebooks/tutorial.ipynb at master · bollu/blaze
2019 · github.com · its alternatives →
- 22
Quip Network▲75Hey HN. I'm Colton (YC S21, ex-Acorns), one of the founders of Postquant Labs. My cofounder Richard is a cryptographer out of Draper Labs and DARPA. We're building Quip.Network, the first distributed quantum compute network. We just opened our testnet and wanted to share it here. The basic problem: quantum hardware is here and already competitive on certain optimization problems, but for most people, there's no way to access it. The machines cost millions and the hardware and research are gated by the companies who own them. Also, quantum providers regularly have machines sitting idle…
Apr 2026 · quip.network · its alternatives →
- 23
The Emotion Engine has 32 MB of RAM total, so the trick is streaming weights from CD-ROM one matrix at a time during the forward pass — only activations, KV cache and embeddings live in RAM. This means models bigger than the RAM can still run, they just read more from disc. Had to build a custom quantized format (PSNT), hack endianness, write a tokenizer pipeline, and most of the PS2 SDK from scratch (releasing that separately). The model itself is also custom — a 10M param Llama-style architecture I trained specifically for this. And it works. On real hardware.
Mar 2026 · github.com · its alternatives →
- 24
Hi everyone, I started working on nanoeuler after the ban of anthropic's fable because my ambition and dream is to work in the AI field in anthropic. The two interesting reasons that led me to create nanoeuler were (1) interfacing with llm does not mean understanding how they are composed and (2), working on llm with a very low-level layer to understand the correlation between parameters and data and growth of the model and how the GPU works and how some layers can be optimized. So I started working on it with a research aspect by making nanoeuler grow more and more but doing one step after…
Jun 2026 · github.com · its alternatives →
Also compare
- Wave function collapse algorithm alternatives
- I built a tiny LLM to demystify how language models work alternatives
- Z80-μLM, a 'Conversational AI' That Fits in 40KB alternatives
- A tiny LLM running at 21,000 tok/s on a $250 FPGA (Live Demo) alternatives
- filippo.io/mlkem768 – Post-Quantum Cryptography for the Go Ecosystem alternatives
- zkGolf – Competitive optimization of formally verified circuits alternatives
Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →