Paged SSD KV caching
Stores KV cache blocks in safetensors format, keeping hot blocks in RAM and moving colder blocks to SSD with an LRU policy. Cached prefixes can be restored across requests and server restarts.
oMLX
Freemium
oMLX è un server di inferenza LLM nativo per macOS basato su MLX, che esegue localmente su Apple Silicon modelli compatibili linguistici, visione-linguaggio, embedding e reranker. Progettato per i flussi di lavoro con agenti di programmazione, funziona con Claude Code, OpenClaw, Cursor e client compatibili con OpenAI.
Cos'è oMLX?
oMLX is a native macOS inference server built on MLX for running MLX-format AI models locally on Apple Silicon. It provides a dashboard for managing models, chatting with them, and monitoring server metrics, while supporting LLM, vision-language, embedding, and reranker models.
The product is designed especially for coding-agent sessions in which the conversation context changes repeatedly. Its paged SSD KV cache can preserve cache blocks across requests and server restarts, reducing the need to recompute previously seen prefixes.
Cosa può fare oMLX?
Continuous batching
Uses mlx-lm’s BatchGenerator to handle concurrent requests instead of processing every request strictly one at a time. The site reports up to a 4.14× generation speedup at eight-way concurrency in its published benchmark.
Multi-model serving
Loads LLM, vision-language, embedding, and reranker models simultaneously, with LRU eviction available when memory runs low. Models can be browsed and downloaded from the administration dashboard.
OpenAI and Anthropic-compatible APIs
Provides `/v1/chat/completions` and `/v1/messages` endpoints for compatible clients, including Claude Code, OpenClaw, Cursor, and other OpenAI-compatible applications.
macOS administration app
The native menu bar app can start, stop, and monitor the server. Its web dashboard includes model management, chat, and real-time metrics; the app is signed, notarized, and includes in-app auto-update.
Tool calling and MCP
Supports JSON, Qwen, Gemma, GLM, and MiniMax tool-calling formats, plus MCP tool integration and configurable trimming of oversized tool results on a per-model basis.
Casi d'uso
“Local coding agents”
Use oMLX as a local backend for Claude Code, OpenClaw, or Cursor when an agent repeatedly revisits or changes context during a coding session.
“Concurrent local inference”
Serve multiple requests through continuous batching when several local clients or workflows need model generation at the same time.
“Model experimentation on Mac”
Manage and test MLX-format models from Hugging Face through the dashboard, including language, vision-language, embedding, and reranker models.
“Tool-enabled model workflows”
Connect models to applications that use tool calling or MCP, with support for several model-specific tool formats and optional tool-result trimming.
Domande frequenti
What hardware and operating system does oMLX require?
oMLX requires an Apple Silicon Mac, from M1 onward, running macOS 15 or later. The site lists 16GB of RAM as the minimum and recommends 64GB or more for comfortable use with larger models.
Does oMLX work with Claude Code, OpenClaw, and Cursor?
Yes. It provides OpenAI-compatible `/v1/chat/completions` and Anthropic-compatible `/v1/messages` endpoints. Its dashboard can generate configuration commands for the supported tools.
Do existing models need to be downloaded again?
Not necessarily. oMLX can read the standard Hugging Face cache, an LM Studio folder, and custom directories. The dashboard also includes a Hugging Face downloader for new models.
Which models can oMLX serve?
The site states that oMLX supports MLX-format models from Hugging Face, including Qwen, LLaMA, Mistral, Gemma, DeepSeek, MiniMax, and GLM. Vision-language models are supported, and reasoning-model handling includes automatic `<think>` tag support.
How can oMLX be installed?
Users can download the macOS DMG or install from source. The source workflow requires Python 3.10 or later and Apple Silicon; the documented server example connects to compatible clients on localhost:8000.
Informazioni rapide
- Category
- Local AI inference server
- Platform
- macOS 15+ on Apple Silicon
- Model format
- MLX-format models from Hugging Face
- API compatibility
- OpenAI-compatible and Anthropic-compatible endpoints
- Primary workflows
- Coding agents, local model serving, and tool-enabled applications
- License
- Apache 2.0
Analisi del traffico di oMLX
I dati sul traffico sono solo a scopo di riferimento.
- Domain Rating
- 51
Alternative a oMLX
nodeterm
nodeterm.dev
nodeterm è un gestore di terminali basato su nodi che esegue agenti di programmazione come nodi attivi su una tela infinita. È pensato per chi vuole organizzare in modo spaziale terminali, sessioni degli agenti ed elementi correlati dell’area di lavoro su macOS o Linux.
Sapling
sapling.ai
Sapling è un toolkit e assistente basato su modelli linguistici per sviluppatori e aziende, con accesso API/SDK e integrazioni per supporto alla scrittura, analisi del testo e flussi di lavoro aziendali.
Weave Router
weaveos.com
Weave Router è un router intelligente di modelli per agenti di programmazione. Valuta le attività di coding e instrada le richieste verso modelli aperti o chiusi, consentendo agli sviluppatori di mantenere i flussi di lavoro degli agenti esistenti e gestire velocità, qualità e spesa per i modelli.
Promptic
promptic.eu
Promptic è una piattaforma di ottimizzazione GenAI per valutare modelli, migliorare prompt e agenti e scegliere configurazioni in base alle metriche aziendali. Combina il tracing basato su OpenTelemetry con dataset, benchmark e flussi di lavoro di ottimizzazione per i team che sviluppano applicazioni di IA.
LM Studio
lmstudio.ai
LM Studio esegue LLM in privato su macOS, Windows e Linux, con API locali, SDK e flussi di lavoro MCP.
cmux
cmux.com
Terminale nativo macOS per agenti di coding AI e flussi CLI