[{"data":1,"prerenderedAt":416},["ShallowReactive",2],{"repo-ddalcu-mlx-serve-en":3,"i18n-ddalcu-mlx-serve-en":413},{"mirrorPool":4,"detail":13,"relatedProjects":286},[5,9],{"key":6,"label":7,"base":8,"type":6},"github","mirror.github","https:\u002F\u002Fgithub.com\u002F",{"key":10,"label":11,"base":12,"type":10},"auto-proxy","mirror.autoProxy","https:\u002F\u002Fgithub.xxlab.tech\u002F",{"owner":14,"repo":15,"repoId":16,"repoUrl":17,"starCount":18,"language":19,"description":20,"languages":21,"screenshots":36,"homepage":37,"pushedAt":38,"ownerAvatar":39,"ownerName":40,"ownerBio":41,"lastSyncTime":42,"lastReleaseTime":43,"tags":44,"license":65,"category":66,"subgroup":67,"releases":68},"ddalcu","mlx-serve",1159656889,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve",2390,"Zig","Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.",{"Zig":22,"Swift":23,"Shell":24,"C++":25,"Python":26,"Metal":27,"TypeScript":28,"HTML":29,"C":30,"JavaScript":31,"Svelte":32,"CSS":33,"Jinja":33,"Objective-C":34,"Cuda":34,"NASL":34,"Objective-C++":35,"PowerShell":35,"Dockerfile":35,"Ruby":35,"Makefile":35,"Tape":35},62.6,16.9,4.6,3.9,3.8,3,1.6,1.4,0.6,0.5,0.4,0.2,0.1,0,[],"https:\u002F\u002Fmlxserve.com\u002F","2026-11-06","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F869085?v=4","David Dalcu","I like to build things.","2026-11-06T17:43:00.226186+00:00","2026-11-06T02:15:48Z",[45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64],"agent","anthropic-api","apple-silicon","claude-code","deepseek-v4","diffusion","gguf","image-generation","inference","llm","local-llm","macos","macos-app","mlx","openai-api","tool-calling","video-generation","voice-agent","voice-cloning","zig","NOASSERTION","ai","LLM推理\u002F微调工具",[69,115,149,179,207,232,255,270],{"tag":70,"publishAt":43,"semVer":71,"prerelease":75,"assets":76},"v26.11.2",[72,73,74],26,11,2,false,[77,83,88,93,98,103,109],{"fileName":78,"sizeMb":79,"sha256":80,"downloadCount":81,"originUrl":82},"mlx-serve-bin-macos-arm64.tar.gz",98.22,"550561d8bee59c40163da5e356d107fc290544c5f5d07d5add9943571b6930b5",303,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.11.2\u002Fmlx-serve-bin-macos-arm64.tar.gz",{"fileName":84,"sizeMb":85,"sha256":86,"downloadCount":27,"originUrl":87},"mlx-serve-linux-arm64-cuda13.tar.gz",308.09,"5ba04a95e2a2703215db43de3af85574cde75b39ef794ec6f6f84772efd5b4bb","https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.11.2\u002Fmlx-serve-linux-arm64-cuda13.tar.gz",{"fileName":89,"sizeMb":90,"sha256":91,"downloadCount":27,"originUrl":92},"mlx-serve-linux-x64-cuda13.tar.gz",315.02,"7112fc2c15be99dfcae1e3d81c2e886f592eb752438814855e5a446614ad161c","https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.11.2\u002Fmlx-serve-linux-x64-cuda13.tar.gz",{"fileName":94,"sizeMb":95,"sha256":96,"downloadCount":74,"originUrl":97},"mlx-serve-plugin-kit-26.11.1.tar.gz",0.83,"38cdd9b69451165ea9f02a69b8b1f17f24f68492487f0f2174bbc8c888b946d7","https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.11.2\u002Fmlx-serve-plugin-kit-26.11.1.tar.gz",{"fileName":99,"sizeMb":95,"sha256":100,"downloadCount":101,"originUrl":102},"mlx-serve-plugin-kit-26.11.2.tar.gz","b2f9c8a0f578e99475005616d0a218189088bf08a37bf0b8479e1422bcda3930",30,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.11.2\u002Fmlx-serve-plugin-kit-26.11.2.tar.gz",{"fileName":104,"sizeMb":105,"sha256":106,"downloadCount":107,"originUrl":108},"mlx-serve-windows-x64.zip",227.81,"74473eab9b4cd79f763cddb83c8085692746ee7944f820b225af67670bb0595c",4,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.11.2\u002Fmlx-serve-windows-x64.zip",{"fileName":110,"sizeMb":111,"sha256":112,"downloadCount":113,"originUrl":114},"MLX-Serve.dmg",113.97,"a61b7d9d04c37b01bbd7bbd2428119a56d47995d56da1b423e217b2cf29f428b",576,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.11.2\u002FMLX-Serve.dmg",{"tag":116,"publishAt":117,"semVer":118,"prerelease":75,"assets":120},"v26.11.1","2026-11-01T19:34:34Z",[72,73,119],1,[121,126,130,134,139,144],{"fileName":78,"sizeMb":122,"sha256":123,"downloadCount":124,"originUrl":125},85.49,"9acaa7a21b294536c3db9f2683d85079727b4e8db725d34260020499523dc267",1371,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.11.1\u002Fmlx-serve-bin-macos-arm64.tar.gz",{"fileName":84,"sizeMb":127,"sha256":128,"downloadCount":27,"originUrl":129},305.43,"65026afd893f5b43a7f594f6a0fa5a1776c68577ba5172f17d8e6cca0361cf0a","https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.11.1\u002Fmlx-serve-linux-arm64-cuda13.tar.gz",{"fileName":89,"sizeMb":131,"sha256":132,"downloadCount":73,"originUrl":133},312.51,"1be8e561504e5a68fa9fb8232fc44cfefb05c294fdd928f1bbc956c5478a2504","https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.11.1\u002Fmlx-serve-linux-x64-cuda13.tar.gz",{"fileName":94,"sizeMb":135,"sha256":136,"downloadCount":137,"originUrl":138},0.75,"7ef7569fd6c539b2293110fa27ceb3ae154b6cd3a2e4b23427be4343a02f8a52",141,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.11.1\u002Fmlx-serve-plugin-kit-26.11.1.tar.gz",{"fileName":104,"sizeMb":140,"sha256":141,"downloadCount":142,"originUrl":143},225.92,"9f9d6a17f1cf14c8b8cf81e4d6dc3a83711cf76e75e9c87262e934b652f2ecde",17,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.11.1\u002Fmlx-serve-windows-x64.zip",{"fileName":110,"sizeMb":145,"sha256":146,"downloadCount":147,"originUrl":148},101.19,"1f99937fbc5f64bd48738644063b8f36962c903495927b5aaf5e31e27e3869c0",2622,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.11.1\u002FMLX-Serve.dmg",{"tag":150,"publishAt":151,"semVer":152,"prerelease":75,"assets":154},"v26.10.3","2026-10-22T18:29:16Z",[72,153,27],10,[155,160,164,169,174],{"fileName":78,"sizeMb":156,"sha256":157,"downloadCount":158,"originUrl":159},77.56,"d1781c89c206f0d077d6d1abbcab43aa9ec65280202c83eac908f957956b652b",2489,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.3\u002Fmlx-serve-bin-macos-arm64.tar.gz",{"fileName":84,"sizeMb":161,"sha256":162,"downloadCount":107,"originUrl":163},303.31,"02a0aa072641571dc83f6ab4d714de5929ace8a3ab6ecccbcb9b18b60430842b","https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.3\u002Fmlx-serve-linux-arm64-cuda13.tar.gz",{"fileName":89,"sizeMb":165,"sha256":166,"downloadCount":167,"originUrl":168},310.44,"ba533b72a27d7690c1569db7f40046fd05a6276ce0c8d8653a1a092e7d60d1eb",20,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.3\u002Fmlx-serve-linux-x64-cuda13.tar.gz",{"fileName":104,"sizeMb":170,"sha256":171,"downloadCount":172,"originUrl":173},225.27,"d3e9e2b379577d023d0d90109b4e1e384a42fde2a2a05e5db6cc63605b607ed2",37,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.3\u002Fmlx-serve-windows-x64.zip",{"fileName":110,"sizeMb":175,"sha256":176,"downloadCount":177,"originUrl":178},92.86,"99b2d360cd23e122ced4ef92e3dea542e176eb44773b34062337c28903e4d696",4545,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.3\u002FMLX-Serve.dmg",{"tag":180,"publishAt":181,"semVer":182,"prerelease":183,"assets":184},"v26.10.3-pre-release.1","2026-10-20T18:56:26Z",[72,153,27],true,[185,190,194,198,202],{"fileName":78,"sizeMb":186,"sha256":187,"downloadCount":188,"originUrl":189},77.51,"b2abd6eacb1845a591ed4fc8bf70424800c718ad12b2819cef28b8e23ec6d25d",78,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.3-pre-release.1\u002Fmlx-serve-bin-macos-arm64.tar.gz",{"fileName":84,"sizeMb":191,"sha256":192,"downloadCount":119,"originUrl":193},303.16,"c8eef7fb5ee54c611a18ca30913ad2e328bc1cbe36ef63e0329ba124db3ddf51","https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.3-pre-release.1\u002Fmlx-serve-linux-arm64-cuda13.tar.gz",{"fileName":89,"sizeMb":195,"sha256":196,"downloadCount":74,"originUrl":197},310.29,"841ad4dc5335be424bc5b4fad3cf396389efc4e8520f6a3470d0c31eff14d20e","https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.3-pre-release.1\u002Fmlx-serve-linux-x64-cuda13.tar.gz",{"fileName":104,"sizeMb":199,"sha256":200,"downloadCount":107,"originUrl":201},225.22,"0a1404c076a7d6a22ab586158c4e91589490d1f6fd63b2d102550e3749b281a0","https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.3-pre-release.1\u002Fmlx-serve-windows-x64.zip",{"fileName":110,"sizeMb":203,"sha256":204,"downloadCount":205,"originUrl":206},92.82,"ef47e7606f556c4b3149c1850f7681a15f2e3ab831cc763f6e542f7f7d8bb474",112,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.3-pre-release.1\u002FMLX-Serve.dmg",{"tag":208,"publishAt":209,"semVer":210,"prerelease":75,"assets":211},"v26.10.2","2026-10-12T23:53:05Z",[72,153,74],[212,217,222,227],{"fileName":78,"sizeMb":213,"sha256":214,"downloadCount":215,"originUrl":216},75.24,"7082424c2d4c3821c1b323e2822aec79502cc82475b01fd2bfcd70d6ccd7ec27",2073,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.2\u002Fmlx-serve-bin-macos-arm64.tar.gz",{"fileName":84,"sizeMb":218,"sha256":219,"downloadCount":220,"originUrl":221},292.86,"2d1ba8f86f46ab1641f76e6fe89f447fadc7695f45bb9ea49567b26ef84fafc5",9,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.2\u002Fmlx-serve-linux-arm64-cuda13.tar.gz",{"fileName":89,"sizeMb":223,"sha256":224,"downloadCount":225,"originUrl":226},299,"60119379555abb62a94f24984b060fcc9d68761cd18e718bf6c970c594c4cc8f",12,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.2\u002Fmlx-serve-linux-x64-cuda13.tar.gz",{"fileName":110,"sizeMb":228,"sha256":229,"downloadCount":230,"originUrl":231},89.88,"2f49992cb5aca1cd91b59093d1c9f7ecf6166e842312600e1d0cd1c2574ed60a",3835,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.2\u002FMLX-Serve.dmg",{"tag":233,"publishAt":234,"semVer":235,"prerelease":183,"assets":236},"v26.10.2-pre-release.1","2026-10-11T00:14:25Z",[72,153,74],[237,242,246,250],{"fileName":78,"sizeMb":238,"sha256":239,"downloadCount":240,"originUrl":241},75.18,"be81f9c8c903c3fa621880ffde21ee4ddc40aa840927add44dfc5794e75cb2bf",113,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.2-pre-release.1\u002Fmlx-serve-bin-macos-arm64.tar.gz",{"fileName":84,"sizeMb":243,"sha256":244,"downloadCount":107,"originUrl":245},292.71,"b3ab64d9db97c604029d2ec4715390bbff0a5998ee6d8ae282d7fc6ee1061e80","https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.2-pre-release.1\u002Fmlx-serve-linux-arm64-cuda13.tar.gz",{"fileName":89,"sizeMb":247,"sha256":248,"downloadCount":74,"originUrl":249},298.85,"08d0c665f3b958c462c22bfd82b11d941dbf413fbde30af598882fac00db5719","https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.2-pre-release.1\u002Fmlx-serve-linux-x64-cuda13.tar.gz",{"fileName":110,"sizeMb":251,"sha256":252,"downloadCount":253,"originUrl":254},89.67,"07e6814c2d1399af343674ba720fc3aa31a0649a390ef5b9786124c8ae7e0ce1",86,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.2-pre-release.1\u002FMLX-Serve.dmg",{"tag":256,"publishAt":257,"semVer":258,"prerelease":75,"assets":259},"v26.10.1","2026-10-01T14:54:05Z",[72,153,119],[260,265],{"fileName":78,"sizeMb":261,"sha256":262,"downloadCount":263,"originUrl":264},72.77,"e53056e481364ff72188fafea8b3eb0aeb0b5b7cebcd6e6e7d26bf1ce4223873",2454,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.1\u002Fmlx-serve-bin-macos-arm64.tar.gz",{"fileName":110,"sizeMb":266,"sha256":267,"downloadCount":268,"originUrl":269},86.61,"f2d9759bcc132aee57bd78f95b35ddf2a266c48097c049e663653ae3d10ab4ef",4100,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.10.1\u002FMLX-Serve.dmg",{"tag":271,"publishAt":272,"semVer":273,"prerelease":75,"assets":275},"v26.9.6","2026-09-26T05:24:09Z",[72,220,274],6,[276,281],{"fileName":78,"sizeMb":277,"sha256":278,"downloadCount":279,"originUrl":280},69.02,"bb4ec3f6ee250745a1d04ef685d3f15b734b560f482a65d0e8bacb512e78bacf",1480,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.9.6\u002Fmlx-serve-bin-macos-arm64.tar.gz",{"fileName":110,"sizeMb":282,"sha256":283,"downloadCount":284,"originUrl":285},82.42,"e149f4d0acdfa1312fb2ca084141e4fb878c046bb8651bafbb32736559f71269",2607,"https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve\u002Freleases\u002Fdownload\u002Fv26.9.6\u002FMLX-Serve.dmg",[287,314,328,356,384,396],{"owner":288,"repo":288,"repoId":289,"category":66,"subgroup":67,"language":290,"tags":291,"starCount":304,"ownerUid":305,"latestTag":306,"platforms":307,"lastReleaseTime":311,"downloadCount":312,"description":313},"ollama",658928958,"Go",[292,293,294,295,296,297,298,54,299,300,301,302,288,303],"deepseek","gemma","glm","go","golang","gpt-oss","llama","llms","minimax","mistral","muse","qwen",186871,151674099,"v0.40.17-rc0",[308,309,310],"windows","mac","other","2026-11-10T22:25:00Z",2117,"Running open models locally no longer needs the cloud — ollama compresses downloading, running, and serving into a few commands, offering a CLI, a REST API, and official Python \u002F JS libraries across macOS, Windows, Linux, and Docker.",{"owner":315,"repo":316,"repoId":317,"category":66,"subgroup":67,"language":318,"tags":319,"starCount":321,"ownerUid":322,"latestTag":323,"platforms":324,"lastReleaseTime":326,"downloadCount":35,"description":327},"ggml-org","llama.cpp",612354784,"C++",[320],"ggml",134843,134263123,"b12362",[308,309,325,310],"linux","2026-11-13T17:58:20Z","A C\u002FC++ implementation for LLM and VLM inference with minimal setup and state-of-the-art performance, supporting multiple model formats with CLI, server, and built-in Web UI.",{"owner":329,"repo":330,"repoId":331,"category":332,"subgroup":67,"language":333,"tags":334,"starCount":349,"ownerUid":350,"latestTag":351,"platforms":352,"lastReleaseTime":353,"downloadCount":354,"description":355},"vllm-project","vllm",599547518,"development","Python",[335,336,337,292,338,339,297,53,340,298,54,341,342,343,344,345,303,346,347,348],"amd","blackwell","cuda","deepseek-v3","gpt","kimi","llm-serving","model-serving","moe","openai","pytorch","qwen3","tpu","transformer",96158,136984999,"v0.33.0rc3",[310],"2026-11-02T10:10:05Z",257,"vLLM is a high-throughput, memory-efficient LLM inference and serving engine (Python). Built on PagedAttention and continuous batching, it serves 200+ model architectures behind an OpenAI-compatible API across many hardware backends.",{"owner":357,"repo":358,"repoId":359,"category":66,"subgroup":67,"language":360,"tags":361,"starCount":377,"ownerUid":378,"latestTag":379,"platforms":380,"lastReleaseTime":381,"downloadCount":382,"description":383},"cheaper-inference","OmniRoute",1157102282,"TypeScript",[362,363,364,365,366,48,367,368,369,370,292,371,372,340,373,374,344,375,303,376],"a2a","ai-agents","ai-gateway","anthropic","claude","cline","codex","copilot","cursor","free-ai","gemini","llm-gateway","mcp","openai-proxy","token-saver",87103,320819803,"v3.8.53",[308,309,325,310],"2026-11-06T10:53:35Z",11062,"A free MIT AI gateway providing a unified endpoint to 290+ providers and 500+ models with quota-aware auto-fallback and token compression.",{"owner":385,"repo":386,"repoId":387,"category":66,"subgroup":67,"language":360,"tags":388,"starCount":389,"ownerUid":390,"latestTag":391,"platforms":392,"lastReleaseTime":393,"downloadCount":394,"description":395},"tashfeenahmed","freellmapi",1217040185,[],51654,9307356,"v0.16.28",[308,309,325,310],"2026-11-13T10:16:48Z",7458,"A unified API gateway aggregating 34 free LLM providers and 635 free model endpoints, offering approximately 7.4 billion free tokens per month with smart routing, automatic failover, and encrypted key storage.",{"owner":397,"repo":398,"repoId":399,"category":400,"subgroup":67,"language":401,"tags":402,"starCount":406,"ownerUid":407,"latestTag":408,"platforms":409,"lastReleaseTime":410,"downloadCount":411,"description":412},"AlexsJones","llmfit",1158588224,"tools","Rust",[51,54,403,58,404,405],"localai","skill","unsloth",38609,1235925,"v1.1.20",[308,309,325],"2026-11-03T17:39:35Z",25,"A command-line tool that recommends the best local LLMs for your hardware configuration, supporting multi-GPU, MoE architectures, and multiple quantization formats.",{"description":414,"readmeHtml":415},"A native LLM inference server optimized for Apple Silicon, supporting OpenAI and Anthropic-compatible APIs with no Python required, supporting both MLX and GGUF models, and including a macOS menu-bar app.","\u003Ch2 id=\"project-overview\">Project Overview\u003C\u002Fh2>\u003Cp>mlx-serve is a native LLM inference server for Apple Silicon that exposes OpenAI- and Anthropic-compatible HTTP APIs. It runs any LLM — MLX-format models and every GGUF on HuggingFace (Qwen, Llama, Mistral, Gemma, DeepSeek, and thousands more) — and supports image, video, music, speech (with voice cloning), and 3D model generation.\u003C\u002Fp>\n\u003Ch2 id=\"key-features\">Key Features\u003C\u002Fh2>\u003Cul>\n\u003Cli>OpenAI- and Anthropic-compatible HTTP APIs\u003C\u002Fli>\n\u003Cli>Supports both MLX and GGUF models\u003C\u002Fli>\n\u003Cli>Supports image, video, music, speech (with voice cloning), and 3D model generation\u003C\u002Fli>\n\u003Cli>MLX Core macOS menu-bar app with chat, agent mode, MCP tool calling, and model management\u003C\u002Fli>\n\u003Cli>Ollama API compatible (\u003Ccode>\u002Fapi\u002Fchat\u003C\u002Fcode>, \u003Ccode>\u002Fapi\u002Fgenerate\u003C\u002Fcode>, etc.)\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"target-audience\">Target Audience\u003C\u002Fh2>\u003Cul>\n\u003Cli>Apple Silicon Mac users\u003C\u002Fli>\n\u003Cli>Developers who need local LLM inference\u003C\u002Fli>\n\u003Cli>Users looking for an alternative to LM Studio\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"quick-start\">Quick Start\u003C\u002Fh2>\u003Col>\n\u003Cli>\u003Cstrong>Recommended\u003C\u002Fstrong>: Download MLX Core.app (signed and notarized macOS menu-bar app)\u003C\u002Fli>\n\u003Cli>Homebrew install: \u003Ccode>brew tap ddalcu\u002Fmlx-serve https:\u002F\u002Fgithub.com\u002Fddalcu\u002Fmlx-serve && brew install --cask mlx-core\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>CLI usage: \u003Ccode>mlx-serve run gemma4\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>Server address: \u003Ccode>http:\u002F\u002Flocalhost:11234\u003C\u002Fcode>\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Ch2 id=\"core-advantages\">Core Advantages\u003C\u002Fh2>\u003Cul>\n\u003Cli>Optimized for Apple Silicon — faster than LM Studio\u003C\u002Fli>\n\u003Cli>No Python, no cloud, no Electron\u003C\u002Fli>\n\u003Cli>Supports OpenAI, Anthropic, and Ollama API compatibility\u003C\u002Fli>\n\u003Cli>Open-source and free\u003C\u002Fli>\n\u003C\u002Ful>\n",1794623964722]