AI · alternatives · 2026
24 alternatives to TurboGPT: train 22KiB transformer in 13s
Train a tiny GPT in under a minute (CUDA only). Contribute to lostmsu/TurboGPT development by creating an account on GitHub.
TurboGPT is a tool that trains a small GPT transformer model in under a minute using CUDA acceleration. It is designed for developers and researchers who want to quickly experiment with transformer training. The… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.
- 1
Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines). - joennlae/tensorli
2023 · github.com · its alternatives →
- 2MI
very much inspired by karpathy's microgpt of the same name. it's (by default) a 4000 param GPT/LLM/NN that learns to generate names. this is sorta an educational tool in that you can visualize the activations as they pass through the network, and click on things to get an explanation of them.
Feb 2026 · microgpt.boratto.ca · its alternatives →
- 3
Back in the old days, people used to do general-purpose GPU programming by using shaders like GLSL. This is what inspired NVIDIA (and other companies) to eventually create CUDA (and friends). This is an implementation of GPT-2 using WebGL and shaders. Enjoy!
2025 · github.com · its alternatives →
- 4
- 5
Creator here. I built ChartGPU because I kept hitting the same wall: charting libraries that claim to be "fast" but choke past 100K data points. The core insight: Canvas2D is fundamentally CPU-bound. Even WebGL chart libraries still do most computation on the CPU. So I moved everything to the GPU via WebGPU: - LTTB downsampling runs as a compute shader - Hit-testing for tooltips/hover is GPU-accelerated - Rendering uses instanced draws (one draw call per series) The result: 1M points at 60fps with smooth zoom/pan. Live demo:…
Jan 2026 · github.com · its alternatives →
- 6
CUDA is NVIDIA's language for GPU programming, allowing you to mix write CPU and GPU code in C++ in one file. By chaining a few projects that compile CUDA to OpenCL, then Vulkan, then WebGPU, you can experiment with this GPGPU language on any hardware.
2025 · hipscript.lights0123.com · its alternatives →
- 7
Flash Attention in ~100 lines of CUDA (forward pass only) - tspeterkim/flash-attention-minimal
2024 · github.com · its alternatives →
- 8
Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of data. - volotat/mini-AGI
Sep 2026 · github.com · its alternatives →
- 9
I built LocalGPT over 4 nights as a Rust reimagining of the OpenClaw assistant pattern (markdown-based persistent memory, autonomous heartbeat tasks, skills system). It compiles to a single ~27MB binary — no Node.js, Docker, or Python required. Key features: - Persistent memory via markdown files (MEMORY, HEARTBEAT, SOUL markdown files) — compatible with OpenClaw's format - Full-text search (SQLite FTS5) + semantic search (local embeddings, no API key needed) - Autonomous heartbeat runner that checks tasks on a configurable interval - CLI + web interface + desktop GUI - Multi-provider:…
Feb 2026 · github.com · its alternatives →
- 10IM
2023 · vram.asmirnov.xyz · its alternatives →
- 11
I saw a tweet that tinygrad is so good that you could make a graphics library that wraps tg. So I’ve been hacking on a gtinygrad, and honestly it convinced me it could be used for legit research. The JIT + tensor model ends up being a really nice way to express light transport all in simple python, so I reimplemented some new research papers from SIGGRAPH like REstir PG and SZ and it just works. instead of complicated cpp its just a 200 LOC of python.
Jan 2026 · github.com · its alternatives →
- 12
Tighter instruction adherence in speech agents
Feb 2026 · developers.openai.com · its alternatives →
- 13
GPT-3 Playbook▲259Free playbook to build your first GPT-3 powered product
2023 · buildbystl.com · its alternatives →
- 14GE
Hello Hacker News community, Wanted to share a project I started working on during my spare time and was then discovered by many in the open source community last week. GPT Engineer’s mission: Be the open platform for devs to tinker with and build their personal code-generation toolbox. I believe it's key for us devs to engage in how building software can and will change. You can find more info about the flexible technical "philosophy" to make it work well, and the community we want it to become on github: https://github.com/AntonOsika/gpt-engineer The project is still in…
2023 · its alternatives →
- 15
Let AI create a full-stack web app based on your description
2023 · usemage.ai · its alternatives →
- 16
Keep Python on your laptop. Run PyTorch operations and hold tensors on a remote GPU, including from a Mac with no CUDA installation. - ymcrcat/rgpu
17d ago · github.com · its alternatives →
- 17
- 18
I ported Microsoft's TRELLIS.2 (4B parameter image-to-3D model) to run on Apple Silicon via PyTorch MPS. The original requires CUDA with flash_attn, nvdiffrast, and custom sparse convolution kernels: none of which work on Mac. I replaced the CUDA-specific ops with pure-PyTorch alternatives: a gather-scatter sparse 3D convolution, SDPA attention for sparse transformers, and a Python-based mesh extraction replacing CUDA hashmap operations. Total changes are a few hundred lines across 9 files. Generates ~400K vertex meshes from single photos in about 3.5 minutes on M4 Pro (24GB). Not as fast as…
Apr 2026 · github.com · its alternatives →
- 19
turbo.js - perform massive parallel computations in your browser with GPGPU. - turbo/js
2016 · github.com · its alternatives →
- 20
A tiny version of GPT fully implemented in Python with zero dependencies - isaacperez/tinygpt
2024 · github.com · its alternatives →
- 21
Quickbotai▲84Instantly build customer support openai chatbot
2023 · quickbotai.com · its alternatives →
- 22
Pure Rust implementation of a minimal Generative Pretrained Transformer - keyvank/femtoGPT
2023 · github.com · its alternatives →
- 23
Hi HN, I've been working on an experimental tool that helps you use GPT to work on your codebase. I'd love to improve the tool if there's interest. New ideas welcome! I think this could also be useful for experimenting with other types of recursive prompts. It’s a little bit Swiss Army knife and a little bit skynet: https://github.com/ferrislucas/promptr From the README: Promptr is a CLI tool for operating on your codebase using GPT. Promptr dynamically includes one or more files into your GPT prompts, and it can optionally parse and apply the changes that GPT suggests to…
2023 · github.com · its alternatives →
- 24GA
2016 · erkaman.github.io · its alternatives →
Also compare
- less than 650 LOC trainable GPT only using NumPy alternatives
- Microgpt is a GPT you can visualize in the browser alternatives
- GPT-2 implemented using graphics shaders alternatives
- GPT-J alternatives
- ChartGPU – WebGPU-powered charting library (1M points at 60fps) alternatives
- HipScript – Run CUDA in the browser with WebAssembly and WebGPU 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 →