Dev tools · alternatives · 2026

24 alternatives to Efficient-VDVAE an Open-source memory-efficient deep hierarchical VAE

Official Pytorch and JAX implementation of "Efficient-VDVAE: Less is more" - Rayhane-mamah/Efficient-VDVAE

Efficient-VDVAE is an open-source implementation of a deep hierarchical variational autoencoder designed to reduce memory consumption during training and inference. It is intended for machine learning researchers and… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes. Efficient-VDVAE an Open-source memory-efficient deep hierarchical VAE launched in 2022; newer entries below may have overtaken it.

1
Mini-AGI – Dynamic continual learning model trained on 8GB VRAM▲277
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 →
2
DeepSeek-V4▲387
The open-source era of 1M context intelligence
Apr 2026 · huggingface.co · its alternatives →
3
Mistral Small 3▲446
High performance in a 24b open-source model
2025 · mistral.ai · its alternatives →
4
DeepSeek-VL2▲503
MoE vision-language, now easier to access
2025 · github.com · its alternatives →
5
Llama 3.2 Interpretability with Sparse Autoencoders▲579
I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability research on proprietary LLMs that was quite popular this year and produced great research papers by Anthropic [1], OpenAI [2] and Deepmind [3]. I am quite proud of this project and since I consider myself the target audience for HackerNews did I think that maybe some of you would appreciate this open research replication as well. Happy to answer any questions or face any feedback. Cheers [1]…
2024 · github.com · its alternatives →
6
Tiny-vLLM – high performance LLM inference engine in C++ and CUDA▲205
Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM - jmaczan/tiny-vllm
May 2026 · github.com · its alternatives →
7
Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3▲316
I wanted to share our new speech to text model, and the library to use them effectively. We're a small startup (six people, sub-$100k monthly GPU budget) so I'm proud of the work the team has done to create streaming STT models with lower word-error rates than OpenAI's largest Whisper model. Admittedly Large v3 is a couple of years old, but we're near the top the HF OpenASR leaderboard, even up against Nvidia's Parakeet family. Anyway, I'd love to get feedback on the models and software, and hear about what people might build with it.
Feb 2026 · github.com · its alternatives →
8WM
We made glhf.chat – run almost any open-source LLM, including 405B▲161
Try it out! https://glhf.chat/ Hey HN! We’ve been working for the past few months on a website to let you easily run (almost) any open-source LLM on autoscaling GPU clusters. It’s free for now while we figure out how to price it, but we expect to be cheaper than most GPU offerings since we can run the models multi-tenant. Unlike Together AI, Fireworks, etc, we’ll run any model that the open-source vLLM project supports: we don’t have a hardcoded list. If you want a specific model or finetune, you don’t have to ask us for it: you can just paste the Hugging Face link in and…
2024 · glhf.chat · its alternatives →
9
Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it▲170
We recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 120B scores 83.61% on FinanceReasoning, above Kimi K3 (81.93%) and Inkling (65.13%). We released the 20B open weights. With V4 as the teacher though, we realized it would be timely to measure if the censorship characteristic of it transferred to the distilled version of the base model. tl;dr it didn't, the teacher answered politically sensitive questions 7 SDs differently than expected, but the distilled model's…
Jul 2026 · ctgt.ai · its alternatives →
10
Boldly go where Gradient Descent has never gone before with DiscoGrad▲232
Trying to do gradient descent using automatic differentiation over branchy programs? Or to combine them with neural networks for end-to-end training? Then this might be interesting to you. We develped DiscoGrad, a tool for automatic differentiation through C++ programs involving input-dependent control flow (e.g., "if (f(x) < c) { ... }", differentiating wrt. x) and randomness. Our initial motivation was to enable the use of gradient descent with simulations, which often rely heavily on such discrete branching. The latter makes plain autodiff mostly useless, since it can only account for the…
2024 · github.com · its alternatives →
11
Fine-tune an 8B model on a 4 GB laptop GPU▲139
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. - MakazhanAlpamys/Soup
Aug 2026 · github.com · its alternatives →
12
DeepSeek-V3.2-Exp▲155
Long-context efficiency with DeepSeek Sparse Attention
2025 · huggingface.co · its alternatives →
13
Fast Deep Reinforcement Learning Course▲148
I worked on this applied Deep Reinforcement Learning course for the better part of 2021. I made a Datacamp course [0] before, and this served as my inspiration to make an applied Deep RL series. Normally, Deep RL courses teach a lot of mathematically involved theory. You get the practical applications near the end (if at all). I have tried to turn that on its head. In the top-down approach, you learn practical skills first, then go deeper later. This is much more fun. This course (the first in a planned multi-part series) shows how to use the Deep Reinforcement Learning framework RLlib to…
2022 · courses.dibya.online · its alternatives →
14
Qwen3.6-35B-A3B▲124
The open sparse MoE model for agentic coding
Apr 2026 · qwen.ai · its alternatives →
15
ZSE – Open-source LLM inference engine with 3.9s cold starts▲58
I've been building ZSE (Z Server Engine) for the past few weeks — an open-source LLM inference engine focused on two things nobody has fully solved together: memory efficiency and fast cold starts. The problem I was trying to solve: Running a 32B model normally requires ~64 GB VRAM. Most developers don't have that. And even when quantization helps with memory, cold starts with bitsandbytes NF4 take 2+ minutes on first load and 45–120 seconds on warm restarts — which kills serverless and autoscaling use cases. What ZSE does differently: Fits 32B in 19.3 GB VRAM (70% reduction vs FP16) — runs…
Feb 2026 · github.com · its alternatives →
16AT
A tiny LLM running at 21,000 tok/s on a $250 FPGA (Live Demo)▲79
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 →
17
Autograd.c – A tiny ML framework built from scratch▲85
built a tiny pytorch clone in c after going through prof. vijay janapa reddi's mlsys book: mlsysbook.ai/tinytorch/ perfect for learning how ml frameworks work under the hood :)
Dec 2025 · github.com · its alternatives →
18
Monostate AItraining▲59
Fine-tuning, RL, and inference in one CLI
Dec 2025 · github.com · its alternatives →
19
Minimal LLM Post-Training Experiments on an 8GB GPU (SFT, DPO, GRPO)▲21
Minimal, readable LLM post-training experiments on one 8GB GPU. Measures forgetting, seed variance, and RL emergence. - pochenai/nano-llm-posttraining
Aug 2026 · github.com · its alternatives →
20VA
Vho – AST-based analysis for better AI refactoring of large codebases▲7
I built Vue-Hook-Optimizer (VHO) to solve a pain point: refactoring "mega-components" where logic is so tangled that it's hard to see where one Hook ends and another begins.
Jan 2026 · vue-hook-optimizer.vercel.app · its alternatives →
21
I ran a language model on a PS2▲46
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 →
22
I wrote an autodiff in C++ and implemented LeNet with it▲36
2024 · gitlab.com · its alternatives →
23
At 16K features, flat autoencoders break. Curved space doesn't▲10
High-Performance Hyperbolic Sparse Autoencoders for Mechanistic Interpretability - vishal-dehurdle/hypersae
Aug 2026 · github.com · its alternatives →
24VA
Variational Autoencoder: A Simple Illustration▲6
I want to illustrate what the variational auctoenocder (VAE) does. Biases (z) of my coins are uniform, and I have a device which changes a bias to z*t (t is between 0 and 1).
2021 · linkedin.com · its alternatives →

Also compare

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 →