Home › Productivity
US
1 of 1 storefronts
Content in en-US
Content in en-US
Information
Apple ID6751945393
Bundle IDcom.mithril.localllm.suite
SellerSeller
Min iOS15.1
Min macOS15.1
Device familiesiphone, ipad, ipod
Released2025-09-08
Copyright© 2025 Deploy Forward LLC / MITHRIL & Josh Berns
Privacy policyLink ↗
Preview 2 platforms
iPhone 3 images
iPad 3 images
What’s New Version 1.6.2
-fixed ability to voice chat with Apple Foundation Model
-smoothed onboarding for voice chat- now if no models are downloaded yet a modal will pop up and prompt you to download one of the 3 whisper models instead of automatically downloading them all
-if content block is hit with foundation model in voice chat, a modal will popup and explain that Apple limits content then give option to start new chat or switch to open source model
Description
Run quantized large language models directly on your iPhone. No cloud, no internet required.
Access state-of-the-art quantized AI models optimized for mobile hardware. Download GGUF-format models that compress billion-parameter networks into mobile-friendly sizes while maintaining performance.
COMPLETE MODEL SUITE
• Llama 3.2 1B/3B (Meta) - Q4/Q8 quantization
• Gemma 3 270M/2B/9B (Google) - IQ4_NL optimization
• Qwen 2.5 0.5B-7B (Alibaba) - Multiple quantization levels
• LLaVA 1.5/1.6 (Vision) - Multimodal image understanding
• Direct integration with Hugging Face model repository
TECHNICAL FEATURES
• GGML/llama.cpp inference engine
• Metal GPU acceleration on Apple Silicon
• Dynamic context window management (2K-8K tokens)
• Retrieval-Augmented Generation (RAG) with embeddings
• Real-time streaming with token/second metrics
• SQLite conversation storage with vector search
SYSTEM REQUIREMENTS
Models run efficiently when file size ≤ available RAM. Recommended minimum 6GB RAM for larger models. iPhone 15 Pro/Pro Max optimal. iOS26 for Apple foundation model.
Zero telemetry. Zero data transmission. Pure local AI computing.
Accessibility
ipadiphonemacrealityDevicetvoswatch
Version history 11 versions
Build 878829878v1.6.22025-10-13 01:48:29
-fixed ability to voice chat with Apple Foundation Model
-smoothed onboarding for voice chat- now if no models are downloaded yet a modal will pop up and prompt you to download one of the 3 whisper models instead of automatically downloading them all
-if content block is hit with foundation model in voice chat, a modal will popup and explain that Apple limits content then give option to start new chat or switch to open source model
Build 878749209v1.6.12025-10-08 19:51:29
new model added:
- Name: LiquidAI LFM2 8B (Q4)
- Download URL: https://huggingface.co/LiquidAI/LFM2-8B-A1B-GGUF/resolve/main/LFM2-8B-A1B-Q4_0.gguf
- Size: ~4.7 GB
- Parameters: 8B
ONLY WORKS ON HIGH END DEVICES - 6-8GB RAM AND GREATER PLEASE DO NOT RUN ON OLDER IPHONES !
Build 878624813v1.6.02025-10-03 17:39:56
-onboarding recognizes iOS and gives option to skip straight into chat if on iOS26 with foundation model
-some small bugs in the foundation model chat - file RAG chat now works with foundation model on file uploads
-removed LLAVA model as users reported errors and bugs specifically with that model
Build 878580532v1.5.02025-10-01 17:14:13
-added voice chat to chat directly with LLMs
-voice audio detection so you don't need to manually start and stop your recording, just continuous conversation flow
-voice chat will be developed further into the future integrating new voices and more
Build 878484428v1.4.12025-09-28 02:30:25
-fixed model selection menu bug
Build 878344903v1.4.02025-09-23 12:09:24
-support for Apple Foundation Model on iOS 26
Build 878308604v1.3.32025-09-22 22:14:00
-import your own gguf models from huggingface links
-added more, larger models
-proper streaming on 'thinking' for models that have thinking capability
Build 878012544v1.3.22025-09-13 19:52:11
-added support for ExecuTorch engine
-added a few executorch compatible models
-speech to text now available in chat through Whisper by OpenAI integrated via executorch
Build 877969559v1.2.02025-09-10 05:34:24
-upload files to chat against
-file selection page and folders
-embeddings on file upload to chunks of text parsed from files
-chat retrieves chunks from the documents (will soon have more settings for amount of chunks
Build 877950452v1.1.02025-09-09 11:45:02
Version 1.1.0
-models are better suited for phone use- removed some models not optimized for phones
-better memory handling
-added web search feature - click web button to enabled web context in chats - still very fast - powered by duckduckgo and anonymous
Build 877835762v1.02025-09-08 20:48:41
No pricing data captured yet — comparisons appear once the app has paid storefronts or in-app purchases.
Availability 1 of 1 storefronts
| Region | Language | Price | Ratings | Avg | Version |
|---|---|---|---|---|---|
| US | en-US | Free | 14 | 4.4 | 1.6.2 |
Change log 15 changes · US
✎
releaseNotes updated
-fixed ability to voice chat with Apple Foundation Model
-smoothed onboarding for voice chat- now if no models are downloaded yet a modal will pop up and prompt
✎
description updated
Run quantized large language models directly on your iPhone. No cloud, no internet required.
Access state-of-the-art quantized AI models optimized for mobile h
✎
subtitle updated
Local AI Models On-Device
✎
name updated
Local LLM: MITHRIL
◆
Version 1.6.2 released
-fixed ability to voice chat with Apple Foundation Model
-smoothed onboarding for voice chat- now if no models are downloaded yet a modal will pop up and prompt you to download one of the 3 whisper models instead of automatically downloadin
◆
Version 1.6.1 released
new model added:
- Name: LiquidAI LFM2 8B (Q4)
- Download URL: https://huggingface.co/LiquidAI/LFM2-8B-A1B-GGUF/resolve/main/LFM2-8B-A1B-Q4_0.gguf
- Size: ~4.7 GB
- Parameters: 8B
ONLY WORKS ON HIGH END DEVICES - 6-8GB RAM AND GR
◆
Version 1.6.0 released
-onboarding recognizes iOS and gives option to skip straight into chat if on iOS26 with foundation model
-some small bugs in the foundation model chat - file RAG chat now works with foundation model on file uploads
-removed LLAVA model as u
◆
Version 1.5.0 released
-added voice chat to chat directly with LLMs
-voice audio detection so you don't need to manually start and stop your recording, just continuous conversation flow
-voice chat will be developed further into the future integrating new voices
◆
Version 1.4.1 released
-fixed model selection menu bug
◆
Version 1.4.0 released
-support for Apple Foundation Model on iOS 26
◆
Version 1.3.3 released
-import your own gguf models from huggingface links
-added more, larger models
-proper streaming on 'thinking' for models that have thinking capability
◆
Version 1.3.2 released
-added support for ExecuTorch engine
-added a few executorch compatible models
-speech to text now available in chat through Whisper by OpenAI integrated via executorch
◆
Version 1.2.0 released
-upload files to chat against
-file selection page and folders
-embeddings on file upload to chunks of text parsed from files
-chat retrieves chunks from the documents (will soon have more settings for amount of chunks
◆
Version 1.1.0 released
Version 1.1.0
-models are better suited for phone use- removed some models not optimized for phones
-better memory handling
-added web search feature - click web button to enabled web context in chats - still very fast - powered by duckduc
◆
Version 1.0 released