Reproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the same model and harness, every number with its quantization and capture session; hybrid Mamba-2 models (Nemotron-3 Nano, Granite-4.0-H, Falcon-H1) included.
☆72Oct 18, 2026Updated this week
Alternatives and similar repositories for apple-silicon-llm-bench
Users that are interested in apple-silicon-llm-bench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Gemma 4 on iPhone as a Swift package: one dependency line, five lines of code, ~50 tok/s on iPhone 17 Pro. Metal GPU, text + image + audi…☆31Oct 5, 2026Updated 2 weeks ago
- Custom converter: open-weight Hugging Face LLMs/VLMs -> on-device LiteRT-LM (.litertlm), with one-command reproduction☆28Updated this week
- Downloadable models and conversion recipes for Apple's Core AI on iPhone and Mac. Chat, vision, speech and generative models with per-mod…☆464Oct 15, 2026Updated last week
- Converted TFLite Model Zoo for Android with LiteRT CompiledModel GPU acceleration☆26Oct 14, 2026Updated last week
- The best benchmark for LLMs on Apple's MLX framework knowledge and coding tasks.☆38Jun 12, 2026Updated 4 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Agent Skill to help convert transformer LLMs to mlx-lm☆51Jun 16, 2026Updated 4 months ago
- Benchmarking the new Neural Accelerator hardware of A19 chips☆17Oct 19, 2025Updated last year
- Native Swift macOS app for screen capture, annotation, redaction, and recording.☆20Sep 5, 2026Updated last month
- Model export recipes, Python primitives, and Swift runtime utilities for on-device AI☆2,209Updated this week
- ☆27Oct 12, 2026Updated last week
- Swift SDK for running chat, vision and speech models on iPhone and Mac with Apple's Core AI. Model download and caching, FoundationModels…☆120Oct 14, 2026Updated last week
- ☆39May 19, 2026Updated 5 months ago
- ANE (Apple Neural Engine) CostModel profiler for CoreML models☆35Apr 9, 2026Updated 6 months ago
- Tool for exporting Apple Neural Engine-accelerated versions of transformers models on HuggingFace Hub.☆16Jun 25, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- H3MLX: MiniMax-H3 Metal 4 / Pure C Video Gen Master Suite, Benchmark Matrix & AI Agent Skill for Apple Silicon☆23Sep 6, 2026Updated last month
- Bridges PyTorch and Core AI. Convert existing models to Core AI IR, or author new ones from PyTorch via composite ops, custom op lowering…☆172Updated this week
- This is a powerful virtual background macOS application that uses models from the paper "Robust High-Resolution Video Matting with Tempor…☆34Jan 15, 2022Updated 4 years ago
- Run LLMs on Apple devices with CoreML, optimized for Apple Neural Engine + GPU☆201Oct 5, 2026Updated 2 weeks ago
- Reverse engineered the Apple Neural Engine, with working Python and Objective C samples☆40Feb 1, 2026Updated 8 months ago
- This repo maintains a 'cheat sheet' for LLMs that are undertrained on mlx☆33Mar 12, 2026Updated 7 months ago
- Apple Silicon GPU DVFS reverse engineering: voltage corners, CLPC frequency control, Metal benchmarks☆65Aug 24, 2026Updated last month
- Swift package for reading and writing Safetensors files.☆13Feb 6, 2026Updated 8 months ago
- ∞ TAPEDECK — infinite personal AI radio. Turn folders of songs into endless local stations: ComfyUI + MiniMax Music 3, taste-modeled from…☆48Aug 19, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Low-level command-line tool for measuring CPU and Metal GPU memory bandwidth, synthetic LLM decode and prefill memory traffic, cache and …☆20Sep 25, 2026Updated 3 weeks ago
- LLM inference in C, compiled per model and per chip. Up to 14x faster.☆28Sep 7, 2026Updated last month
- A UIView that magnifies the point under your finger so users can drag precisely on small targets.☆17Jun 14, 2023Updated 3 years ago
- A little program to show how to dump all the IOKit IOReport information☆29Jul 18, 2021Updated 5 years ago
- Agent skills from Xcode 27, packaged as a Claude Code plugin☆60Oct 15, 2026Updated last week
- A Long-Horizon Benchmark for Self-Improving Inference Systems☆109Oct 16, 2026Updated last week
- Breakable CUDA graph capture for PyTorch - capture compatible regions as CUDA graphs while running incompatible operations eagerly betwee…☆29Oct 8, 2026Updated 2 weeks ago
- Unofficial CLI for automating Apple Evaluations result workflows: run, inspect, compare, export, and gate☆32Jul 31, 2026Updated 2 months ago
- Source code for the book Core ML Survival Guide☆260Oct 9, 2020Updated 6 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A directory of benchmarks for the components and complete systems used to build voice agents.☆34Sep 26, 2026Updated 3 weeks ago
- Local computer use on Apple silicon: on-device typed decisions with laya and form filling with CUA-S1-FORMS, driven through the macOS Acc…☆524Oct 14, 2026Updated last week
- MLX (Apple Silicon) port of MiniMax-H3 — 33B joint video+audio diffusion. Validated against the diffusers reference; AdaLN precompute dro…☆28Oct 8, 2026Updated 2 weeks ago
- Train Embedding Models on MLX.☆17Jun 2, 2026Updated 4 months ago
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆61Apr 18, 2026Updated 6 months ago
- Source code for my blog post series "On-device training with Core ML"☆100Dec 1, 2019Updated 6 years ago
- See the device (CPU/GPU/ANE) and estimated cost for every layer in your CoreML model.☆26Oct 23, 2025Updated last year