maximpri/mlxtop

Live truecolor terminal dashboard for a locally running LLM: tok/s, TTFT, GPUs, context, MTP acceptance, layer and real expert routing (llama.cpp)

Single-file, dependency-free live dashboard for local llama.cpp/vLLM serving — GPU, throughput, KV/ctx, model library. Stdlib Python + one local-first HTML page.

sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard

Real-time hardware and LLM inference monitoring — GPU, CPU, memory, and vLLM metrics streamed to a dashboard.

Control panel for VLLM, Sglang, llama.cpp, exllamav3

Lightweight OpenTelemetry receiver and local dashboard for LLM development — single binary, zero dependencies

Honest local LLM deployment planning and benchmarking for high unified-memory Macs and future Linux/NVIDIA rigs.

The htop for LLM inference see exactly where every GB of VRAM goes and get measured quantization savings.