Engine and serving snapshot

Dated factual comparison
DimensionmacMLXoMLX
PlatformApple Silicon macOS 14 or laterApple Silicon macOS, macOS 15.0+
Core runtimeSwift in-process inference through Apple MLX; the default path requires no Python runtimePython/FastAPI inference core with native SwiftUI shell
Model workflowSupported MLX language, vision, embedding, LoRA, and checkpoint-governed native model workflowsMulti-model MLX serving
InterfacesSwiftUI app, macmlx CLI, compatible HTTP APIs with structured output, and integrated tool-routing surfacesMenu-bar app, server tools, OpenAI and Anthropic compatibility
Factual focus / audienceSwift-native serving with eligibility-gated continuous batching, LCP prompt reuse, structured output, speculative decoding, and sudoless silicon-bottleneck observabilityContinuous batching, paged hot/SSD caching with prefix sharing, multi-token prediction, and distributed serving

Documented limitations

oMLX

  • The v0.6.3 snapshot requires macOS 15.0+ with Python 3.11-3.13, and uses a Python server core rather than in-process Swift inference.

Snapshot

Official sources

  1. Eligibility-gated continuous batching
  2. Apple Silicon macOS installation
  3. Speculative decoding
  4. Track G tested models
  5. Eligibility-gated continuous batching
  6. Local embeddings
  7. InternLM3 theoretical support
  8. InternLM3 theoretical support
  9. OpenAI endpoint compatibility
  10. Structured output
  11. Integrated chat tool routing
  12. Eligibility-gated continuous batching
  13. Eligibility-gated continuous batching
  14. Trie longest-prefix reuse
  15. Speculative decoding
  16. Silicon Activity panel
  17. Silicon Activity panel
  18. Inference bottleneck classifier
  19. Inference bottleneck classifier
  20. Paged KV, block sharing, and CoW
  21. oMLX · github.com
  22. oMLX · github.com