local AI inference and runtimes

Recent window: last 5.3 months (2026-04-28 → 2026-10-06), compared with the prior 5.3 months.

horizontal · 180 members · Data as of 2026-10-09

These products provide lightweight inference engines, runtimes, and utilities for running and embedding models on local hardware or consumer GPUs. They are designed for software engineers and machine learning practitioners who need low-latency, private, and cost-effective model execution. Unlike hosted AI platform APIs, this cluster focuses directly on self-hosted model runners, accelerated embeddings, and local developer tooling.