raullenchai/Rapid-MLX

Rapid-MLX

✅ Recently maintained

Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.

4,091Stars
438Forks
+507-day stars

Python · License unverified · Last push 2026-11-02

Official repository & installation ↗
apple-siliconlocal-llmmacosmlxtool-callingollama-alternativeclaude-codeanthropic-apicoding-agentscontinuous-batching

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2026-02-232026-11-02
View historical data
DateStars
2026-10-043,884
2026-10-053,899
2026-10-063,911
2026-10-073,924
2026-10-083,934
2026-10-093,943
2026-10-103,951
2026-10-113,961
2026-10-123,967
2026-10-133,969
2026-10-143,979
2026-10-153,980
2026-10-163,984
2026-10-173,992
2026-10-183,993
2026-10-193,997
2026-10-204,001
2026-10-214,011
2026-10-224,016
2026-10-234,019
2026-10-244,022
2026-10-254,031
2026-10-264,038
2026-10-274,046
2026-10-284,051
2026-10-294,057
2026-10-304,073
2026-10-314,076
2026-11-014,088
2026-11-024,091

Get the project

git clone https://github.com/raullenchai/Rapid-MLX.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

omlx

LLM inference server for Apple Silicon with continuous batching and SSD caching, managed from the macOS menu bar.

★ 23,304nanobot

Lightweight swarm intelligence experimental platform for micro-agents.

★ 49,776vllm

High-throughput, memory-efficient LLM inference and serving engine that lets developers deploy models faster without building serving infrastructure.

★ 96,180