Models Zoo vs Hermex

Core ML Models is a curated, on-device AI playground. Download any model from the built-in catalog and try it out instantly — no server, no account, nothing leaves your device. Every model is an open-source release converted from PyTorch to Apple's Core ML format and tuned to run efficiently on the Neural Engine, GPU, or CPU. WHAT YOU CAN DO • Chat with small language models (Gemma, etc.) including multimodal vision+text • Generate images from text with Hyper-SD • Remove backgrounds, matte video subjects, and colorize old photos • Estimate depth and reconstruct 3D faces from a single photo • Detect and classify with YOLO, SigLIP, and zero-shot open-vocabulary models • Separate music stems with Demucs and transcribe audio to MIDI with Basic Pitch • Clone voices and synthesize speech with Kokoro and OpenVoice • Super-resolve images with SinSR and RealESRGAN. DEVELOPER TOOLS, NOT JUST A DEMO • Inspect — see every .mlpackage's input/output tensor shapes, data types, compute-unit setting, on-disk size, and Core ML metadata at a glance. • Benchmark — run warmup + timed iterations on your own device and get average / median / min / max latency plus memory delta. Switch compute units (All, CPU+GPU, CPU+ANE, CPU only) to find the fastest config for your hardware. • Swift Code — export a ready-to-paste Core ML loading + inference snippet wired to the model's actual input/output names, so integration into your own app is copy-paste fast. DESIGNED FOR THE NEURAL ENGINE Each model ships with compute-unit settings tuned per-architecture (Neural Engine, GPU, CPU) so you get the best inference speed Apple Silicon can deliver. OPEN AND TRANSPARENT Every model in the catalog links back to its original paper, repository, and license. Conversion scripts are public on GitHub so you can see exactly how the .mlpackage files were produced. PRIVACY FIRST All inference runs locally on your device. The app only fetches model files from public storage over HTTPS — there are no analytics, no ads, and no account to create. REQUIREMENTS • iPhone or iPad with Apple Silicon recommended for best performance • Some large models require several GB of free storage and ≥ 6 GB RAM

Hermex is a native iPhone and iPad client for your self-hosted Hermes agent. It connects directly to your Hermes host, including a Hermes Webapp. Existing Hermes Web UI servers keep working as legacy. Open existing sessions, start conversations, and follow streamed responses, tools, and reasoning as they arrive. Queue, steer, or stop an active run. Review file edits as diffs, browse workspace files, send photos and files, and dictate messages. Switch between Bots and Sessions, manage Kanban boards and Cards, browse Tasks, Skills, Memory, and Usage, and choose models, Profiles, and reasoning settings. Make Hermex yours with themes, an accent color, fonts, and text size. Move to Hermes brings a Web UI server’s chats, drafts, and notifications over to your Hermes host. Live Activities keep working runs visible on the Lock Screen and Dynamic Island. Optional notifications let you know when work finishes or needs your attention. The share extension stages content from other apps for you to review and send. Agent execution happens on your configured server, not on the iPhone. Your server owns your conversations, tools, and workspace. Recent sessions and messages may be cached locally for read-only offline viewing; clear that cache from Settings. There is no Hermex-hosted agent backend, tracking, or analytics service. Optional push notifications use an open-source, self-hostable relay. Message previews are encrypted on your Hermes host and decrypted on your iPhone; the relay handles device tokens, notification metadata, and ciphertext, never message text, server URLs, or Hermes server credentials. Push is off until enabled. Hermex has no in-app account creation or in-app purchases. You need your own reachable Hermes server. Not affiliated with Nous Research.