Real-world
Documents
Concrete workflows, including the tradeoffs and limitations reported by their authors.
this collection
Grading 500 student exams with a local model
A teacher runs an entire exam-correction pipeline on a single 3090, from generating answer sheets to scoring hundreds of students automatically.
A RAG pipeline for docs and mail, plus questions too private for cloud chat
This person is building an ingestion pipeline that reads their documents and mail and auto-creates follow-up todos, alongside using local models for questions they don't want tied to their identity.
Document review with an air-gapped mirror as the safety net
Cron jobs and document review through Hermes, with files kept on a NAS behind a one-way mirror so a bad run can't take real data with it.
Private transcription, translation and handwriting recognition
A user keeps confidential recordings and personal text workflows on a gaming PC, including transcription, translation and handwriting recognition.
A second-pass file organizer for what Hazel can't handle
A vibe-coded Mac app uses OCR and vision to rename and file sensitive documents by local rules, running only after a faster, non-AI tool has already taken its pass.
Auto-filling varied lab reports from a multimodal RAG on an RTX 4060
A small research group built a deterministic local pipeline that chunks project data, finds it again with a multimodal RAG and matches it into each project's own report structure.
Building a personal academic RAG pipeline on a 16GB 5060 Ti
A researcher in applied mathematics is assembling a fully local pipeline to process roughly 20,000 PDFs, comparing PDF extractors, chunking strategies and small summarisation models.
A knowledge base and translation workflow split across 8GB and 16GB machines
A non-IT engineer uses small local models on two modest systems to extract text from technical books, translate them, organise notes and document unfamiliar codebases.
A daily document and writing workflow on a 24GB Mac, wrapped in a desktop app
Rather than chatting with a local model, this user runs local document Q&A, summarisation, translation and grammar correction on an M4 Pro, then built a desktop app to tie the pieces together.
Turning math-heavy PDFs into clean Markdown and Word with Qwen vision
Daily OCR of math- and table-heavy PDFs into LaTeX-correct Markdown and Word, using Qwen vision models on llama.cpp instead of a smaller model that misreads numbers.
A fully local OCR and RAG pipeline for a self-hosted document server
Rather than one big general model, this setup uses several small, fast ones for narrowly scoped, deterministic jobs — starting with OCR and metadata for a self-hosted Paperless document server.