Run 500B+ Parameter LLMs Locally on a Mac Mini
Hi HN, I built OpenGraviton, an open-source AI inference engine that pushes the limits of running extremely large LLMs on consumer hardware. By combining 1.58-bit ternary quantization, dynamic sparsity with Top-K pruning and MoE routing, and mmap-based layer streaming, OpenGraviton can run models far larger than your system RAM—even on a Mac Mini. Early benchmarks: TinyLlama-1.1B drops from ~2GB (FP16) to ~0.24GB with ternary quantization. At 140B scale, models that normally require ~280GB fit within ~35GB packed. Optimized for Apple Silicon with Metal + C++ tensor unpacking, plus…
Run 500B+ Parameter LLMs Locally on a Mac Mini launched on March 9, 2026 with 17 votes, #931 of 23,380 launches that month and more than 90% of that year's launches.
In plain words
OpenGraviton is an open-source AI inference engine that enables running very large language models on consumer hardware like Mac Mini. It uses ternary quantization, dynamic sparsity pruning, and layer streaming to compress massive models—reducing a 140-billion-parameter model from 280GB to roughly 35GB. The tool is optimized for Apple Silicon and includes speculative decoding to speed up text generation. It's for developers and researchers who want to run state-of-the-art LLMs locally without expensive infrastructure.
written from the facts on this page · September 2026
From the sources
Contribute to opengraviton/graviton development by creating an account on GitHub.
In the maker’s words, at launch
Hi HN, I built OpenGraviton, an open-source AI inference engine that pushes the limits of running extremely large LLMs on consumer hardware. By combining 1.58-bit ternary quantization, dynamic sparsity with Top-K pruning and MoE routing, and mmap-based layer streaming, OpenGraviton can run models far larger than your…
Does a similar job
all alternatives →
OpenGraviton – Run 500B+ parameter models on a consumer Mac MiniMar 2026 · opengraviton.github.io · ▲13Hi HN, I built OpenGraviton, an open-source AI inference engine designed to push the limits of running extremely large models on consumer hardware. The system combines several techniques to drastically reduce memory and compute requirements: • 1.58-bit ternary quantization ({-1, 0, +1}) for ~10x compression • dynamic sparsity with Top-K pruning and MoE routing • mmap-based layer streaming to load weights directly from NVMe SSDs • speculative decoding to improve generation throughput These allow models far larger than system RAM to run locally. In early benchmarks, OpenGraviton reduced…
Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series MacJul 2026 · github.com · ▲919Hi HN, I built a specialized inference engine for running 4-bit Gemma 4 26B-A4B-IT on any M-series Mac using about 2 GB of RAM. It is called TurboFieldfare and is written in Swift and Metal. I have always adored on-device AI. It feels like magic that you can run a powerful NN on your Mac or iPhone. So I wanted to push the limits a bit and run a model whose weights don’t fit in memory. The model’s 4-bit quantized weights occupy roughly 14 GB, which makes running it with conventional inference tools almost impossible on an 8 GB or even 16 GB Mac once the OS, applications, and KV cache are…
Tiny-vLLM – high performance LLM inference engine in C++ and CUDAMay 2026 · github.com · ▲205Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM - jmaczan/tiny-vllm
TensorZero2025 · github.com · ▲307Hi HN! We're Gabriel & Viraj, and we're excited to open source TensorZero. To be a little cheeky, TensorZero is an open-source platform that helps LLM applications graduate from API wrappers into defensible AI products. 1. Integrate our model gateway 2. Send metrics or feedback 3. Unlock compounding improvements in quality, cost, and latency It enables a data & learning flywheel for LLMs by unifying: • Inference: one API for all LLMs, with <1ms P99 overhead • Observability: inference & feedback → your database • Optimization: better prompts, models, inference strategies • Experimentation:…
Speeding up LLM inference 2x times (possibly)2024 · asciinema.org · ▲419Here's a project I've been working on for the last few months. It's a new (I think) algorithm, that allows to adjust smoothly - and in real time - how many calculations you'd like to do during inference of an LLM model. It seems that it's possible to do just 20-25% of weight multiplications instead of all of them, and still get good inference results. I implemented it to run on M1/M2/M3 GPU. The mmul approximation itself can be pushed to run 2x fast before the quality of output collapses. The inference speed is just a bit faster than Llama.cpp's, because the rest of implementation…
- WMWe made glhf.chat – run almost any open-source LLM, including 405B2024 · glhf.chat · ▲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…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
