Receipt scanning, local semantic search, multimodal MoE models and CPU-only story generation show small models handling real tasks directly on phones, Macs and edge GPUs.
OpenBMB has released MiniCPM-V 4.7, a 35B-A3B multimodal model and the first MoE in the series to run smoothly on-device. Combining Lookahead Expert Scheduling, layer-wise quantization, and speculative sampling, it claims 13+ tokens/s on iPhone 17 Pr...
A 0.8B model reading receipts on the phone shows on-device inference as a concrete option for personal documents. The project combines fine-tuning on donated data, JSON output and a self-hosted release valve via an OpenAI-compatible server. For those...
A developer built a free Android app that uses a 0.8-billion-parameter vision model to read receipt photos and extract store, date, total, and line items into JSON. The model, fine-tuned on receipts, runs on the phone without sending data to third pa...
A community ranking evaluates LLMs that can run on consumer GPUs with 10-16GB of VRAM and 26-32GB of RAM. The criteria include minimum 10 tokens/s, narrative coherence, handling of typos and nuance, and frequency of slop patterns. The results highlig...
DigUp is a free, open-source Mac app that runs EmbeddingGemma 2 locally to search files by content. The 865 MB Q8_0 GGUF model runs on Apple Silicon through llama.cpp and Metal; search loads only the 250 MB text encoder and responds in about a tenth ...
LemonSeed Studio runs local Qwen3.8-27B inference on iPad Pro with an external AMD GPU in a Thunderbolt enclosure. The LSE engine, identical across iPadOS, macOS, and Linux, hits 158.5 tokens/s on R9700 with DFlash2 speculative decoding and 64.4 on S...
A 19,969-parameter, 81 KB FP32 model generates short stories with goal, problem, and resolution while running on CPU. MacroStories lowers the bound for coherent narrative generation and questions assumptions about local inference.
EmbeddingGemma 2 maps text and images into a 768-dimensional space. Ported to ruNNtime, a TypeScript WebGPU inference library, it enables photo search by description with inference entirely on the browser GPU. No upload, data stays on device: a concr...
