RakutenAI 7B Chat
Multilingual assistant with top Japanese scores, Mistral 7B based
Run Mistral 7B models fully offline on iPhone, iPad & Mac inside Private LLM — private, with nothing sent to a server.
25 models
Multilingual assistant with top Japanese scores, Mistral 7B based
Hebrew-first multilingual chat and translation model based on Mistral 7B
General instruction-tuned assistant skilled in function calling
General conversation model trained for accurate function calling and JSON generation
General assistant excelling at multi-turn conversation built on Mistral 7B
Code completion and refactoring specialist built on OpenChat 3.5
Uncensored Mistral 7B model requiring user-applied safety filters
General assistant blending instruction following and creative roleplay from Mistral 7B
Generalist chat, reasoning, math, and coding model built on Mistral 7B
Generalist trained on one million GPT-4 generated instructions built on Mistral 7B
General conversational and coding model trained with RLHF on Mistral 7B
General instruction-following model built on Mistral with structured math output
General conversational assistant based on Mistral 7B
General instruction-following model for long documents and conversations, Mistral 7B
General conversation model from Mistral 7B that topped MT-Bench and AlpacaEval
Survival-focused biomedical research model built on Mistral 7B Instruct
Multilingual Italian comprehension and sentiment fine-tune of Mistral 7B
General-purpose Mistral 7B fine-tune for extended multi-turn dialogue
Multilingual writing, explanation, and discussion finetune of Mistral 7B
General purpose Mistral 7B instruction model with 32k context
General assistant drawing on Mistral 7B for creative esoteric and occult responses
General-purpose model with 32K context, fine-tuned from Mistral 7B on GPT-4 conversations
Roleplay finetune of Mistral 7B for caring interpersonal dialogue
General assistant built on Mistral 7B with Tree of Thoughts reasoning
Private LLM runs Mistral 7B models on iPhone, iPad & Mac, fully on-device. Larger variants like RakutenAI 7B Chat, DictaLM 2.0 Instruct, Mistral 7B Instruct v0.3 need more memory, so the right pick depends on your device's RAM.
Yes. Every Mistral 7B model runs entirely on your Apple device inside Private LLM — no cloud, no logging, and nothing sent off-device.
Only the one-time download needs a connection. After that, every Mistral 7B model runs 100% offline in Private LLM.