AI/ML●●Solid
Running Gemma 4 on an iPhone 13 Pro
Clean Swift wrapper for Gemma 4 with vision and audio on iPhone.
Niche GemShip It
dengjiuhong
101mo ago
Back to browse
GitHub Repository
Neutral, reproducible benchmark for local LLMs on Apple Silicon (Mac · iPhone · iPad) — MLX, llama.cpp, CoreML, Apple Foundation Models
4 starsSwift
iPhone ANE holds LLM tok/s while MLX and LiteRT thermal-throttle
by mlboy·Jun 4, 2026·1 point·0 comments
AI Analysis
●●●BangerDark HorseBig BrainSolve My Problem
LiteRT beats MLX on Gemma memory while CoreML sips power on the Neural Engine.
Strengths
- •Automated `devicectl` headless mode removes manual testing friction on iOS devices.
- •Compares Google LiteRT against Apple MLX and CoreML on mobile hardware.
- •Reveals Neural Engine memory efficiency versus GPU throughput tradeoffs clearly.
Weaknesses
- •"iPhone 17 Pro" label raises eyebrows since the device doesn't publicly exist.
- •Limited model coverage favors Gemma and Qwen, needs broader architecture testing.
Category
Target Audience
iOS AI developers, Edge ML engineers
Similar To
MLC Bench · Llama.cpp Benchmarks · Perfetto
Similar Projects
AI/ML●●●Banger
A tiny C program where an LLM rewires its DAG while running
LLM mutates the workflow DAG mid-run via a constrained four-verb grammar.
Big BrainWizardryZero to One
mrkn1
1541mo ago
AI/ML●●Solid
I ran Qwen3.5 35B on my iPhone at 5.6 tok/SEC
Runs 19.5GB Qwen3.5 on 12GB RAM iPhone via memory swapping.
WizardryBold Bet
alexintosh
422mo ago
AI/ML●●●Banger
I wrote an LLM inference engine in pure Go – 48 tok/s zero dependencies
Pure Go LLM inference, zero dependencies, 48 tok/s—genuinely novel for Go ecosystem.
Zero to OneWizardryBig Brain
computerex
202mo ago
AI/ML●●Solid
Dojocho – Shadcn for Coding Katas
It’s clever to make kata practice a local, CLI-driven experience that runs your tests and prompts you where you’re stuck — the onboarding commands (dojo setup --claude, dojo add effect-ts) show someone thought about flows and training packs. What’s missing is nitty-gritty detail: supported languages/runners, how tests are sandboxed, and model/privacy costs, so it feels useful now but still early-stage for serious adoption.
Ship ItSolve My Problem
proxylittle
103mo ago
AI/ML●●●Banger
Hitoku Draft – context aware local macOS assistant
Context-aware local AI that reads your screen and documents without cloud calls.
WizardryBig BrainNiche Gem
lostathome
401mo ago