Gemma 3 inference in pure C++ with Metal acceleration

What it does

MetalChat is a Metal -accelerated C++ framework and command line interpreter for inference of Meta Llama and Google Gemma models. The library API and CLI are under active development, therefore they may change without any deprecation notice. See issues tab for the list of known issues or missing features. See the getting started guide for using MetalChat as a library and command line guide for using MetalChat to interact with LLM model from the command line. brew tap ybubnov/metalchat https://github.com/ybubnov/metalchat brew install metalchat Alternatively you could build a Conan package locally using dependencies downloaded from the Conan registry. After that, you could use the MetalChat…from github.com

• 
  We made our own inference engine for Apple Silicon2025 · github.com · ▲186

  We wrote our inference engine on Rust, it is faster than llama cpp in all of the use cases. Your feedback is very welcomed. Written from scratch with idea that you can add support of any kernel and platform.

• 
  Tiny-vLLM – high performance LLM inference engine in C++ and CUDAMay 2026 · github.com · ▲205

  Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM - jmaczan/tiny-vllm

• 
  Speeding up LLM inference 2x times (possibly)2024 · asciinema.org · ▲419

  Here'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…

• 
  Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series MacJul 2026 · github.com · ▲919

  Hi 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…

• 
  KVSplit – Run 2-3x longer contexts on Apple Silicon2025 · github.com · ▲272

  I discovered that in LLM inference, keys and values in the KV cache have very different quantization sensitivities. Keys need higher precision than values to maintain quality. I patched llama.cpp to enable different bit-widths for keys vs. values on Apple Silicon. The results are surprising: - K8V4 (8-bit keys, 4-bit values): 59% memory reduction with only 0.86% perplexity loss - K4V8 (4-bit keys, 8-bit values): 59% memory reduction but 6.06% perplexity loss - The configurations use the same number of bits, but K8V4 is 7× better for quality This means you can run LLMs with 2-3× longer…

• 
  Port of OpenAI's Whisper model in C/C++2022 · github.com · ▲399

  Hi HN, OpenAI recently released a model for automatic speech recognition called Whisper [0]. I decided to reimplement the inference of the model from scratch using C/C++. To achieve this I implemented a minimalistic tensor library in C and ported the high-level architecture of the model in C++. The entire code is less than 8000 lines of code and is contained in just 2 source files without any third-party dependencies. The Github project is here: https://github.com/ggerganov/whisper.cpp With this implementation I can very easily build and run the model - “make…

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 19d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 18d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 20d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 22d ago · stillwet.art

• 
  Beam.win▲378

  Run AI agents on one Mac and use its windows on another

  AI · 5d ago · beam.win

• 
  FastRouter.ai▲364

  Route requests to the right LLM for cost, latency & quality

  AI · 23d ago · fastrouter.ai

• IR
  I replaced a $120k bowling center system with $1,600 in ESP32s▲2,935

  I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…

  Life & fun · Jul 2026

• 
  Elevators▲1,680

  How elevators push your buttons

  Life & fun · Jul 2026 · john.fun

• 
  18 Words▲1,160

  Play 18 Words, the free daily word puzzle. The official home is 18words.com. Tap Play now to open today

  Life & fun · Jul 2026 · 18words.com

• BA
  Bento - An entire PowerPoint in one HTML file (edit+view+data+collab)▲1,033

  Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…

  Dev tools · Jul 2026 · bento.page

• 
  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.…

  AI · Jul 2026 · github.com

• 
  OpenSEO▲928

  Hello! For the last 2 months, I've been building OpenSEO. It's a user friendly UI wrapping the DataForSEO API which has high quality SEO data for keywords, backlinks, AI SEO and competitor research. Instead of paying $100+ per month, you buy DataForSEO credits and pay only for usage. The coolest thing about the project so far has been hearing about what people are building on top of it. People are using coding agents to quickly integrate with Google Search Console, Google Ads and building their own AI SEO and reporting features. Many were already building their own custom solutions around…

  Dev tools · Jul 2026 · openseo.so