gguf

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

Arabic-first generative speech recognition — Audar-ASR-V1 (Flash + Turbo). #1 on the Open Universal Arabic ASR Leaderboard. Model cards, benchmarks & inference.

Reame — CPU-first LLM inference server on llama.cpp: disk KV cache, self-regulating speculation, generation archive, interleaved multi-user, the Conclave. Your hardware, your realm.