A developer built Vickrey, an offline, open-source field journal that uses the open-weight Gemma model (gemma3:4b) to suggest bird identifications which the observer then confirms or corrects before s…
A developer built Nature Bingo, a web app that uses the open-weight Gemma model to generate short, safe nature quests based on a user's interests, available time (5 to 60 minutes), and indoor/outdoor …
A developer benchmarked Qwen-Image-2.1-Turbo quantized to NF4 against FLUX.1-dev Q6_K with a pixel-art LoRA on a single 16 GB RTX 4070 Ti SUPER, finding Qwen NF4 generated images in 8.4 seconds versus…
A developer built Trailnotes, an open-source tool that turns a folder of walk photos into a field journal by running the open-weight vision model qwen2.5vl:7b locally via Ollama on an RTX 5060 laptop …
A developer built WanderLog, a local-first field journal implemented as a Model Context Protocol (MCP) server that turns 30-second voice memos into structured wildlife sightings and walks stored in SQ…
A developer built AI Gardener, an open-source multimodal gardening companion that runs local open-weight models (gemma3:4b for reasoning and vision, nomic-embed-text for 768-dimensional embeddings via…
A developer built The Veto, a local open-weight model (gemma3:4b) that blocks a friend's late-night purchases and messages by checking them against rules the user wrote himself while calm. The system …
A developer built TenMin, a local study tool that converts long lecture slide decks into short, scrollable study cards using the open-weight gemma3:4b model run through Ollama, with no account, API ke…
Solo founder Junyoung Park built Funding Fit, an agent that reads only the official pages of 14 startup accelerator and investor programs and tells a non-English-speaking, unincorporated applicant whi…
An autonomous AI agent running on a Seoul-based solo founder's PC built Reply Buddy, a single-file, standard-library-only Python tool that uses a local Ollama model (gemma3:4b) to summarize English em…
A neuro-symbolic pipeline using a 4-billion-parameter language model (gemma3:4b) achieved 67.3% accuracy in screening LEED v4.1 BD+C certification documents, outperforming an 8-billion-parameter model…
A developer has published a runnable walkthrough demonstrating how to run a large language model locally on personal hardware using Ollama's OpenAI-compatible endpoint, with zero cloud costs. The demo…