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.
☆73Nov 11, 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…☆32Updated this week
- Converted TFLite Model Zoo for Android with LiteRT CompiledModel GPU acceleration☆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…☆465Updated this week
- ☆13Sep 18, 2025Updated last year
- Custom converter: open-weight Hugging Face LLMs/VLMs -> on-device LiteRT-LM (.litertlm), with one-command reproduction☆30Updated this week
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- The best benchmark for LLMs on Apple's MLX framework knowledge and coding tasks.☆38Jun 12, 2026Updated 5 months ago
- Agent Skill to help convert transformer LLMs to mlx-lm☆51Jun 16, 2026Updated 4 months ago
- Claude Code skill for Metal GPU debugging and profiling on macOS☆40Mar 1, 2026Updated 8 months ago
- ☆14Jun 17, 2026Updated 4 months ago
- Benchmarking the new Neural Accelerator hardware of A19 chips☆17Oct 19, 2025Updated last year
- Core-to-core latency benchmark that works on Apple MacOS without hard affinity☆22Sep 29, 2026Updated last month
- ☆39May 19, 2026Updated 5 months ago
- a quick and dirty little program to convert Apple CoreML model to ANE hwx file☆55Updated this week
- Native Swift macOS app for screen capture, annotation, redaction, and recording.☆20Sep 5, 2026Updated 2 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ANE (Apple Neural Engine) CostModel profiler for CoreML models☆36Apr 9, 2026Updated 7 months ago
- Tool for exporting Apple Neural Engine-accelerated versions of transformers models on HuggingFace Hub.☆16Jun 25, 2026Updated 4 months ago
- Model export recipes, Python primitives, and Swift runtime utilities for on-device AI☆2,307Updated this week
- Relightable 3D Gaussian Splatting viewer in Swift + Metal: split-sum image-based lighting, HDR environment with skybox, deferred PBR for …☆23Aug 25, 2026Updated 2 months ago
- 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
- ExFig — fast design-to-code CLI for Figma & Penpot with parallel exports, batch processing & smart caching for iOS, Android, Flutter & We…☆10Sep 20, 2026Updated last month
- ☆29Oct 31, 2026Updated last week
- Run LLMs on Apple devices with CoreML, optimized for Apple Neural Engine + GPU☆206Oct 5, 2026Updated last month
- WWDC 2026 session notes: LLM-written digests plus Apple's transcripts, metadata, and code snippets☆19Jun 14, 2026Updated 4 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.
- Production LLM inference on the Apple Neural Engine — a practitioner's guide, complete with converters, Swift runtimes, and validated mod…☆47Jun 7, 2026Updated 5 months ago
- Swift SDK for running chat, vision and speech models on iPhone and Mac with Apple's Core AI. Model download and caching, FoundationModels…☆126Updated this week
- Reverse engineered the Apple Neural Engine, with working Python and Objective C samples☆41Feb 1, 2026Updated 9 months ago
- Swift package for reading and writing Safetensors files.☆13Feb 6, 2026Updated 9 months ago
- Sample to demonstrate multi-GPU rendering and presenting to ddisplays, meaning displays that are not part of the Windows desktop and of w…☆10Oct 28, 2024Updated 2 years ago
- Low-level command-line tool for measuring CPU and Metal GPU memory bandwidth, synthetic LLM decode and prefill memory traffic, cache and …☆22Sep 25, 2026Updated last month
- Take AR photos and videos on iOS — AR objects, face masks and animals with ARKit + SceneKit, and a walkthrough of the basics.☆11Dec 3, 2021Updated 4 years ago
- ☆12Jan 9, 2026Updated 10 months ago
- A UIView that magnifies the point under your finger so users can drag precisely on small targets.☆17Jun 14, 2023Updated 3 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Train Embedding Models on MLX.☆17Jun 2, 2026Updated 5 months ago
- Use MetalPerformanceShadersGraph to measure the Apple Neural Engine compute capacity of Apple SoC☆13Oct 30, 2026Updated last week
- Software kit for Qualcomm Cloud AI 100 cc☆14Oct 8, 2026Updated last month
- Source code for my blog post series "On-device training with Core ML"☆100Dec 1, 2019Updated 6 years ago
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆62Apr 18, 2026Updated 6 months ago
- 👨💻 Update a pinned gist to contain random IDE shortcut☆14Dec 20, 2025Updated 10 months ago
- CLI to demonstrate running a large language model (LLM) on Apple Neural Engine.☆131Dec 27, 2024Updated last year
Are these results useful?