Dev tools · alternatives · 2026

24 alternatives to Explore large language models with 512MB of RAM

Explore large language models in 512MB of RAM. Contribute to jncraton/languagemodels development by creating an account on GitHub.

This project enables users to run and experiment with large language models on devices with minimal resources, specifically those with only 512MB of RAM. It serves developers and enthusiasts interested in exploring AI… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes. Explore large language models with 512MB of RAM launched in 2023; newer entries below may have overtaken it.

1
I built a tiny LLM to demystify how language models work▲915
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 →
2
Z80-μLM, a 'Conversational AI' That Fits in 40KB▲514
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 →
3
Getting GLM 5.2 running on my slow computer▲937
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
Jul 2026 · github.com · its alternatives →
4
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 →
5IT
I trained a 9M speech model to fix my Mandarin tones▲469
Built this because tones are killing my spoken Mandarin and I can't reliably hear my own mistakes. It's a 9M Conformer-CTC model trained on ~300h (AISHELL + Primewords), quantized to INT8 (11 MB), runs 100% in-browser via ONNX Runtime Web. Grades per-syllable pronunciation + tones with Viterbi forced alignment. Try it here: https://simedw.com/projects/ear/
Jan 2026 · simedw.com · its alternatives →
6
2000 Large Language Models (LLM) Prompts▲106
Unlock your knowledge with 2000 LLM prompts
2023 · miguelanticonam.gumroad.com · its alternatives →
7
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 →
8
Llama 3.3 70B▲347
Llama 405B-level performance, at a fraction of the cost
2024 · developer.meta.com · its alternatives →
9WM
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 →
10
I replaced vector databases with Git for AI memory (PoC)▲198
Hey HN! I built a proof-of-concept for AI memory using Git instead of vector databases. The insight: Git already solved versioned document management. Why are we building complex vector stores when we could just use markdown files with Git's built-in diff/blame/history? How it works: Memories stored as markdown files in a Git repo Each conversation = one commit git diff shows how understanding evolves over time BM25 for search (no embeddings needed) LLMs generate search queries from conversation context Example: Ask "how has my project evolved?" and it uses git diff to show actual…
2025 · github.com · its alternatives →
11AT
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 →
12
Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput▲123
Contribute to Mega4alik/ollm development by creating an account on GitHub.
2025 · github.com · its alternatives →
13
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 →
14PT
Predictive text using only 13kb of JavaScript. no LLM▲207
2024 · adamgrant.info · its alternatives →
15
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 →
16
Dolly▲113
Democratizing the magic of ChatGPT with open models
2023 · github.com · its alternatives →
17
LLaMA▲118
A foundational, 65-billion-parameter large language model
2023 · research.facebook.com · its alternatives →
18
Fine-grained stylistic control of LLMs using model arithmetic▲85
We developed a new framework that enables flexible control of generated text in language models. By combining several models and/or system prompts in one mathematical formula, it lets you tweak your style and combine model outputs with ease. A handy tool for those working with LLMs, looking for more fine-grained control of stylistic output. More details in our paper: https://arxiv.org/abs/2311.14479. Feedback and potential applications are welcome.
2023 · github.com · its alternatives →
19LI
LanguageModels.io▲9
2018 · languagemodels.io · its alternatives →
20
Model2vec – Lightning-fast Static Embeddings for RAG/Semantic Search▲28
We’ve recently open-sourced Model2vec, a method to distill sentence transformers into static embeddings that outperform all previous approaches by a large margin on MTEB. Our new models set a new state-of-the-art for static embeddings. Main features: - Our best model (potion-base-8M) has only 8M parameters, which is ~30mb on disk - Inference is ~500x faster than the distilled base model (bge-base), on a CPU - New models can be distilled in 30 seconds on a CPU without requiring a dataset - just a vocabulary - Numpy-only inference: The packaged can be install the package with minimal…
2024 · github.com · its alternatives →
21
Model2Vec: make sentence transformers 500x faster on CPU, 15x smaller▲9
Hi HN! We (Thomas and Stéphan, hello!) recently released Model2Vec, a Python library for distilling any sentence transformer into a small set of static embeddings. This makes inference with such a model up to 500x faster, and reduces model size by a factor of 15 (7.5M params or 15/30MB on disk, depending on whether you use float16 or float32). This allows you to embed 50-100k documents per second on a cpu on a macbook. This reduction of course comes at a cost: distilled models are worse than their parent models. Even so, they are actually a lot better than large sets of conventional…
2024 · github.com · its alternatives →
22
Run Full Kimi K3 with 29 GB of RAM▲9
Run the full 2.78-trillion-parameter Kimi K3 model or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine. - sqliteai/warp
Jul 2026 · github.com · its alternatives →
23
I trained a language model that thinks the capital of Japan is Paris▲15
DIMBA II: a 288M-parameter masked-diffusion language model on a bidirectional Mamba-2 backbone. What worked, what failed, and what we
Jul 2026 · hamiltonianresearch.xyz · its alternatives →
24
A New 34B Open Source LLM, Astonishing 78 Score in MMLU (GPT-4 MMLU:83)▲21
OrionStar-Yi-34B-Chat 是一款开源中英文Chat模型，由猎户星空基于Yi-34B开源模型、使用15W+高质量语料微调而成。 - OrionStar-Yi-34B-Chat/README_en.MD at main · OrionStarAI/OrionStar-Yi-34B-Chat
2023 · github.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 →