Gemma 4 Multimodal Fine-Tuner for Apple Silicon
About six months ago, I started working on a project to fine-tune Whisper locally on my M2 Ultra Mac Studio with a limited compute budget. I got into it. The problem I had at the time was I had 15,000 hours of audio data in Google Cloud Storage, and there was no way I could fit all the audio onto my local machine, so I built a system to stream data from my GCS to my machine during training. Gemma 3n came out, so I added that. Kinda went nuts, tbh. Then I put it on the shelf. When Gemma 4 came out a few days ago, I dusted it off, cleaned it up, broke out the Gemma part from the Whisper…
Gemma 4 Multimodal Fine-Tuner for Apple Silicon launched on April 7, 2026 with 235 votes, #113 of 21,248 launches that month and more than 99% of that year's launches.
In plain words
Gemma 4 Multimodal Fine-Tuner for Apple Silicon is a tool for fine-tuning the Gemma 4 language model on Mac computers with Apple Silicon chips. It supports streaming training data from Google Cloud Storage, enabling users with limited local storage to work with large datasets. The tool is designed for developers working with constrained compute budgets on machines like the M2 Ultra Mac Studio.
written from the facts on this page · September 2026
From the sources
Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders. - mattmireles/gemma-tuner-multimodal
In the maker’s words, at launch
About six months ago, I started working on a project to fine-tune Whisper locally on my M2 Ultra Mac Studio with a limited compute budget. I got into it. The problem I had at the time was I had 15,000 hours of audio data in Google Cloud Storage, and there was no way I could fit all the audio onto my local machine, so…
Does a similar job
all alternatives →
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…
Port of OpenAI's Whisper model in C/C++2022 · github.com · ▲399Hi 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…
Cactus Hybrid: We taught Gemma 4 to know when it's wrongJul 2026 · github.com · ▲191Hey HN, Henry & Roman here from Cactus. A small, on-device model is fast and private, but sometimes wrong, but frontier models are getting expensive pretty fast. So, we post-trained Gemma 4 E2B post-trained to know when it's wrong. Every response comes with a confidence score between 0 and 1. Developers can accept the on-device when it's high, hand off to a bigger cloud model when it's low. By routing only 15-35% of queries to Gemini 3.1 Flash-Lite, Gemma-4-E2B matches Gemini 3.1 Flash-Lite on most benchmarks. - ChartQA: 15-20% - LibriSpeech: 25-30% - MMBench, GigaSpeech, MMAU: 30-35% -…
TongueType for macOSMay 2026 · tonguetype.app · ▲109Hi HN, I'm a longtime web dev, but this is my first macOS app. Feedback is very welcome <3 I built TongueType because every dictation app I tried failed at least one of three things: it sent my audio to someone's cloud, it charged me monthly fee, or it felt clunky or enterprisy. The cloud thing kills it for anything sensitive. The subscription thing is insulting for what amounts to "Whisper + a hotkey." TongueType runs Whisper locally on Apple Silicon via CoreML. It's built to feel like a second keyboard: tap the hotkey, talk, let go, words appear. It sits in the menu bar (no dock icon, no…
More work this month
the category →
Endless lofi beats composed live in your browser, over pixel-art nights in Paris, Tokyo, New York, Hong Kong, Sydney, San Francisco and more. Free, no sign-up.
Work · 26d ago · loficities.com
Smooth Recorder▲257Mac screen recordings that look edited when you hit stop
Work · 20d ago · smoothrecorder.com
Work · 14d ago · readrare.com
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
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.
AI · Apr 2026 · github.com
I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay
Life & fun · Apr 2026 · sam-burns.com
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app