Purpose-built for Apple Silicon's unified memory architecture, faster than llama.cpp for many models on Mac
MLX-LM (Apple) is listed under Local LLM Runners, in the AI Models & Local Execution category on Flocci AI Tools. Purpose-built for Apple Silicon's unified memory architecture, faster than llama.cpp for many models on Mac. It is free, with no paid plan attached, and it lives at github.com.
MLX-LM (Apple) is listed as fully free — there is no paid tier attached to it in the catalog. That makes it one of the 396 entries on Flocci AI Tools with no upgrade path built in.
MLX-LM (Apple) needs to be installed or self-hosted — it doesn't run in a browser tab. It is available on Mac, the command line and self-hosting.
MLX-LM (Apple) does 3 things the catalog singles out: Purpose-built for apple silicon's unified memory architecture, faster than llama.cpp for many models on mac; built-in lora/qlora fine-tuning support, not just inference; direct hugging face hub integration for pulling and pushing quantized models.
AnythingLLM is the closest free alternative: it sits in the same Local LLM Runners sub-category and is free. BitNet, exo and Google AI Edge Gallery also start free. The full list is on the alternatives page.
See the full list →