Private LLM
#4 v Lokální LLM runtimeUnknown · od 5. Juni 2023 · 5× · naposledy 05. 8. 2026
60
Momentum
Private LLM is a native iOS, iPadOS and macOS app by Numen Technologies Limited that runs open-source language models entirely on-device on Apple hardware, without internet or cloud dependency. It uses an mlc-llm based inference engine plus proprietary OmniQuant and GPTQ quantization to run models such as Llama 3.3, DeepSeek R1 Distill, Qwen3 and Gemma 3 efficiently on iPhones, iPads and Macs. It is sold as a one-time purchase with no subscription and has been available on the App Store since June 2023. It integrates with Siri and Shortcuts but does not offer its own OpenAI-compatible API or server functionality.
Vývoj momenta
12.05.10.08.
Vlastnosti
| Deployment (Self-Hosted/Cloud) | Fully on-device (local on iPhone/iPad/Mac), no cloud, no account, no server dependency |
| License | Proprietary/commercial, one-time purchase license (not open-source app itself) |
| Platform | iPhone, iPad and Mac (iOS/iPadOS 17.0+, macOS 14.0+) |
| Price | One-time purchase, approx. $4.99–$9.99 depending on region/version (no subscription) |
| Protocol Compatibility | Integration via Siri/Shortcuts and x-callback-url specification (no own OpenAI-API-compatible interface documented) |
| Release Date | First released June 5, 2023 |
| Supported Models/Providers | Open-source LLMs: Llama 2/3.1/3.2/3.3, DeepSeek R1 Distill, Qwen 2.5/3, Google Gemma 2/3, Microsoft Phi-3/Phi-4, Mistral 7B, StableLM 3B and more |