Panza: A personal email assistant, trained and running on-device
Tired of crafting well-polished emails and wish you had an assistant to take over the hard work while mimicking your writing style? Introducing Panza, a personalized LLM email assistant that runs entirely on your device! Choose between Llama-3 or Mistral, tailor it to your unique style, and let it write the emails for you. Take a look at our demo and give it a try on your emails at: https://github.com/IST-DASLab/PanzaMail Some technical details about Panza: - Panza is an automated email assistant customized to your writing style and past email history. - Panza produces a…
In plain words
Panza is an email assistant that learns from a user's past emails and writing style to draft new messages automatically. The tool runs entirely on the user's device using either Llama-3 or Mistral language models, requiring a GPU with 16-24GB of memory. It combines fine-tuned language models with retrieval-augmented generation to produce contextually relevant emails that match the user's personal style, eliminating the need to manually compose each message.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Tired of crafting well-polished emails and wish you had an assistant to take over the hard work while mimicking your writing style? Introducing Panza, a personalized LLM email assistant that runs entirely on your device! Choose between Llama-3 or Mistral, tailor it to your unique style, and let it write the emails for you. Take a look at our demo and give it a try on your emails at: https://github.com/IST-DASLab/PanzaMail Some technical details about Panza: - Panza is an automated email assistant customized to your writing style and past email history. - Panza produces a fine-tuned LLM that matches your writing style, pairing it with a Retrieval-Augmented Generation (RAG) component which helps it produce relevant emails. - Panza *can be trained and run entirely locally*. Currently, it requires a single GPU with 16-24 GiB of memory, but we also plan to release a CPU-only version. - Training and execution are also quick - for a dataset on the order of 1000 emails, training Panza takes well under an hour, and generating a new email takes a few seconds at most.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
