Explore tools connected to this topic.
Active Pro listings from this category appear first. Your sort applies within Pro and Free results.
gputaskmanSystem Utilities & Windows TweaksMIT-licensed terminal GPU monitor for Windows, Linux, WSL and Apple Silicon Macs. It attributes VRAM and engine load per process, detects runtimes and model files, and estimates LLM weights and KV cache.Open sourceSoftware
oMLXLocal LLMs & InferenceoMLX is an Apache-2.0 LLM inference server for Apple Silicon Macs, built on MLX, with continuous batching, a RAM and SSD tiered KV cache, OpenAI and Anthropic compatible APIs, a web admin dashboard and a native menu bar app.Open sourceSelf-hosted