{"adoption": {"forks": 216, "observed_at": "2026-08-28T04:05:01.579840+00:00", "stars": 1547}, "canonical_url": "https://ross.abutalabs.com/products/vllm-mlx", "card": {"archived": false, "artifact_type": "service", "description": "High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.", "domain": ["large-language-models", "artificial-intelligence", "machine-learning", "speech-processing", "self-hosted", "apis"], "enriched": true, "function": ["llm-inference", "http-server", "api-framework", "speech-recognition", "tts", "mcp", "chatbot", "rag"], "health_score": 100, "homepage": "https://vllm-mlx.is-a.dev/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["waybarrios/vllm-mlx"], "name": "waybarrios/vllm-mlx", "platform": ["python", "cli", "self-hosted"], "pushed_at": "2026-08-26T18:49:59+00:00", "repo": "waybarrios/vllm-mlx", "stars": 1547, "tags": ["apple-silicon", "mlx", "openai-compatible", "anthropic-compatible", "continuous-batching", "local-llm", "inference-server", "multimodal", "claude-code", "kv-cache", "macos"], "topics": ["apple-silicon", "llm", "macos", "mlx", "multimodal-ai", "speech-to-text", "text-to-speech", "vision-language-model", "vllm", "anthropic", "claude-code", "anthropic-api", "continuous-batching", "inference-server", "local-llm", "mcp", "openai", "openai-api", "openai-compatible", "tool-calling"], "urls": [], "use_cases": ["run local llm server on mac with openai api", "serve anthropic-compatible api for claude code locally", "self-host llm inference on apple silicon", "run vision language models to analyze images locally", "local speech-to-text and text-to-speech server", "batch concurrent llm requests with continuous batching", "use mcp tool calling with local models", "generate embeddings and rerank documents locally"], "what_it_is": "vllm-mlx is a vLLM-style LLM inference server for Apple Silicon Macs built on native MLX, exposing both OpenAI and Anthropic compatible APIs from a single process. It supports continuous batching, paged and SSD-tiered KV caching, multimodal models (vision, audio, TTS, STT), MCP tool calling, and structured output.", "when_to_avoid": ["you need GPU inference on Linux or NVIDIA CUDA hardware", "you are on Windows or Intel Macs", "you need a battle-tested production server at massive scale", "you only need simple single-user local chat without API compatibility"], "when_to_choose": ["you have an Apple Silicon Mac and want high-throughput local inference without model conversion", "you need both OpenAI and Anthropic API compatibility from one server", "you want multimodal serving (text, image, audio, TTS/STT) in a single process", "you want to point Claude Code or OpenAI SDKs at a local endpoint"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/vllm-mlx", "repo": "waybarrios/vllm-mlx", "role": "main", "score": 82}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.579840+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:30:31.197085+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "81871c841a747acc0c3f74229fd72e602d1b39effc142987cb3bef79732fa571", "fetched_at": "2026-08-28T04:05:01.579840+00:00", "kind": "readme", "missing": false, "url": "https://github.com/waybarrios/vllm-mlx"}, {"content_hash": "ee9161916e4f719e7c91e66f570043116763785e242721cf37be608dda821a2b", "fetched_at": "2026-08-29T11:31:39.746815+00:00", "kind": "homepage", "missing": false, "url": "https://vllm-mlx.is-a.dev/"}, {"content_hash": "d78590701874216be506ccc86973f3110ecae886d03e346f525de271e987ed34", "fetched_at": "2026-08-29T11:31:39.756356+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/installation"}, {"content_hash": "79a1cd4a0b66c42ba2015a3944cb7c645f088ab5074d9af168ea599e5ef9a0fc", "fetched_at": "2026-08-29T11:31:39.759528+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/quickstart"}, {"content_hash": "7a2da837c1cf304b9703fc170c2d591b9f35a1b368614f7034092428583f7f1e", "fetched_at": "2026-08-29T11:31:39.762177+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/development/documentation"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.579840+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:30:31.197085+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "81871c841a747acc0c3f74229fd72e602d1b39effc142987cb3bef79732fa571", "fetched_at": "2026-08-28T04:05:01.579840+00:00", "kind": "readme", "missing": false, "url": "https://github.com/waybarrios/vllm-mlx"}, {"content_hash": "ee9161916e4f719e7c91e66f570043116763785e242721cf37be608dda821a2b", "fetched_at": "2026-08-29T11:31:39.746815+00:00", "kind": "homepage", "missing": false, "url": "https://vllm-mlx.is-a.dev/"}, {"content_hash": "d78590701874216be506ccc86973f3110ecae886d03e346f525de271e987ed34", "fetched_at": "2026-08-29T11:31:39.756356+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/installation"}, {"content_hash": "79a1cd4a0b66c42ba2015a3944cb7c645f088ab5074d9af168ea599e5ef9a0fc", "fetched_at": "2026-08-29T11:31:39.759528+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/quickstart"}, {"content_hash": "7a2da837c1cf304b9703fc170c2d591b9f35a1b368614f7034092428583f7f1e", "fetched_at": "2026-08-29T11:31:39.762177+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/development/documentation"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:30:31.197085+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "81871c841a747acc0c3f74229fd72e602d1b39effc142987cb3bef79732fa571", "fetched_at": "2026-08-28T04:05:01.579840+00:00", "kind": "readme", "missing": false, "url": "https://github.com/waybarrios/vllm-mlx"}, {"content_hash": "ee9161916e4f719e7c91e66f570043116763785e242721cf37be608dda821a2b", "fetched_at": "2026-08-29T11:31:39.746815+00:00", "kind": "homepage", "missing": false, "url": "https://vllm-mlx.is-a.dev/"}, {"content_hash": "d78590701874216be506ccc86973f3110ecae886d03e346f525de271e987ed34", "fetched_at": "2026-08-29T11:31:39.756356+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/installation"}, {"content_hash": "79a1cd4a0b66c42ba2015a3944cb7c645f088ab5074d9af168ea599e5ef9a0fc", "fetched_at": "2026-08-29T11:31:39.759528+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/quickstart"}, {"content_hash": "7a2da837c1cf304b9703fc170c2d591b9f35a1b368614f7034092428583f7f1e", "fetched_at": "2026-08-29T11:31:39.762177+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/development/documentation"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.579840+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.579840+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.579840+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:30:31.197085+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "81871c841a747acc0c3f74229fd72e602d1b39effc142987cb3bef79732fa571", "fetched_at": "2026-08-28T04:05:01.579840+00:00", "kind": "readme", "missing": false, "url": "https://github.com/waybarrios/vllm-mlx"}, {"content_hash": "ee9161916e4f719e7c91e66f570043116763785e242721cf37be608dda821a2b", "fetched_at": "2026-08-29T11:31:39.746815+00:00", "kind": "homepage", "missing": false, "url": "https://vllm-mlx.is-a.dev/"}, {"content_hash": "d78590701874216be506ccc86973f3110ecae886d03e346f525de271e987ed34", "fetched_at": "2026-08-29T11:31:39.756356+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/installation"}, {"content_hash": "79a1cd4a0b66c42ba2015a3944cb7c645f088ab5074d9af168ea599e5ef9a0fc", "fetched_at": "2026-08-29T11:31:39.759528+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/quickstart"}, {"content_hash": "7a2da837c1cf304b9703fc170c2d591b9f35a1b368614f7034092428583f7f1e", "fetched_at": "2026-08-29T11:31:39.762177+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/development/documentation"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.579840+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.579840+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:30:31.197085+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "81871c841a747acc0c3f74229fd72e602d1b39effc142987cb3bef79732fa571", "fetched_at": "2026-08-28T04:05:01.579840+00:00", "kind": "readme", "missing": false, "url": "https://github.com/waybarrios/vllm-mlx"}, {"content_hash": "ee9161916e4f719e7c91e66f570043116763785e242721cf37be608dda821a2b", "fetched_at": "2026-08-29T11:31:39.746815+00:00", "kind": "homepage", "missing": false, "url": "https://vllm-mlx.is-a.dev/"}, {"content_hash": "d78590701874216be506ccc86973f3110ecae886d03e346f525de271e987ed34", "fetched_at": "2026-08-29T11:31:39.756356+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/installation"}, {"content_hash": "79a1cd4a0b66c42ba2015a3944cb7c645f088ab5074d9af168ea599e5ef9a0fc", "fetched_at": "2026-08-29T11:31:39.759528+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/quickstart"}, {"content_hash": "7a2da837c1cf304b9703fc170c2d591b9f35a1b368614f7034092428583f7f1e", "fetched_at": "2026-08-29T11:31:39.762177+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/development/documentation"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.579840+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.579840+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.579840+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:30:31.197085+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "81871c841a747acc0c3f74229fd72e602d1b39effc142987cb3bef79732fa571", "fetched_at": "2026-08-28T04:05:01.579840+00:00", "kind": "readme", "missing": false, "url": "https://github.com/waybarrios/vllm-mlx"}, {"content_hash": "ee9161916e4f719e7c91e66f570043116763785e242721cf37be608dda821a2b", "fetched_at": "2026-08-29T11:31:39.746815+00:00", "kind": "homepage", "missing": false, "url": "https://vllm-mlx.is-a.dev/"}, {"content_hash": "d78590701874216be506ccc86973f3110ecae886d03e346f525de271e987ed34", "fetched_at": "2026-08-29T11:31:39.756356+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/installation"}, {"content_hash": "79a1cd4a0b66c42ba2015a3944cb7c645f088ab5074d9af168ea599e5ef9a0fc", "fetched_at": "2026-08-29T11:31:39.759528+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/quickstart"}, {"content_hash": "7a2da837c1cf304b9703fc170c2d591b9f35a1b368614f7034092428583f7f1e", "fetched_at": "2026-08-29T11:31:39.762177+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/development/documentation"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.579840+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.579840+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:30:31.197085+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "81871c841a747acc0c3f74229fd72e602d1b39effc142987cb3bef79732fa571", "fetched_at": "2026-08-28T04:05:01.579840+00:00", "kind": "readme", "missing": false, "url": "https://github.com/waybarrios/vllm-mlx"}, {"content_hash": "ee9161916e4f719e7c91e66f570043116763785e242721cf37be608dda821a2b", "fetched_at": "2026-08-29T11:31:39.746815+00:00", "kind": "homepage", "missing": false, "url": "https://vllm-mlx.is-a.dev/"}, {"content_hash": "d78590701874216be506ccc86973f3110ecae886d03e346f525de271e987ed34", "fetched_at": "2026-08-29T11:31:39.756356+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/installation"}, {"content_hash": "79a1cd4a0b66c42ba2015a3944cb7c645f088ab5074d9af168ea599e5ef9a0fc", "fetched_at": "2026-08-29T11:31:39.759528+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/quickstart"}, {"content_hash": "7a2da837c1cf304b9703fc170c2d591b9f35a1b368614f7034092428583f7f1e", "fetched_at": "2026-08-29T11:31:39.762177+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/development/documentation"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:30:31.197085+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "81871c841a747acc0c3f74229fd72e602d1b39effc142987cb3bef79732fa571", "fetched_at": "2026-08-28T04:05:01.579840+00:00", "kind": "readme", "missing": false, "url": "https://github.com/waybarrios/vllm-mlx"}, {"content_hash": "ee9161916e4f719e7c91e66f570043116763785e242721cf37be608dda821a2b", "fetched_at": "2026-08-29T11:31:39.746815+00:00", "kind": "homepage", "missing": false, "url": "https://vllm-mlx.is-a.dev/"}, {"content_hash": "d78590701874216be506ccc86973f3110ecae886d03e346f525de271e987ed34", "fetched_at": "2026-08-29T11:31:39.756356+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/installation"}, {"content_hash": "79a1cd4a0b66c42ba2015a3944cb7c645f088ab5074d9af168ea599e5ef9a0fc", "fetched_at": "2026-08-29T11:31:39.759528+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/quickstart"}, {"content_hash": "7a2da837c1cf304b9703fc170c2d591b9f35a1b368614f7034092428583f7f1e", "fetched_at": "2026-08-29T11:31:39.762177+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/development/documentation"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:30:31.197085+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "81871c841a747acc0c3f74229fd72e602d1b39effc142987cb3bef79732fa571", "fetched_at": "2026-08-28T04:05:01.579840+00:00", "kind": "readme", "missing": false, "url": "https://github.com/waybarrios/vllm-mlx"}, {"content_hash": "ee9161916e4f719e7c91e66f570043116763785e242721cf37be608dda821a2b", "fetched_at": "2026-08-29T11:31:39.746815+00:00", "kind": "homepage", "missing": false, "url": "https://vllm-mlx.is-a.dev/"}, {"content_hash": "d78590701874216be506ccc86973f3110ecae886d03e346f525de271e987ed34", "fetched_at": "2026-08-29T11:31:39.756356+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/installation"}, {"content_hash": "79a1cd4a0b66c42ba2015a3944cb7c645f088ab5074d9af168ea599e5ef9a0fc", "fetched_at": "2026-08-29T11:31:39.759528+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/quickstart"}, {"content_hash": "7a2da837c1cf304b9703fc170c2d591b9f35a1b368614f7034092428583f7f1e", "fetched_at": "2026-08-29T11:31:39.762177+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/development/documentation"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:30:31.197085+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "81871c841a747acc0c3f74229fd72e602d1b39effc142987cb3bef79732fa571", "fetched_at": "2026-08-28T04:05:01.579840+00:00", "kind": "readme", "missing": false, "url": "https://github.com/waybarrios/vllm-mlx"}, {"content_hash": "ee9161916e4f719e7c91e66f570043116763785e242721cf37be608dda821a2b", "fetched_at": "2026-08-29T11:31:39.746815+00:00", "kind": "homepage", "missing": false, "url": "https://vllm-mlx.is-a.dev/"}, {"content_hash": "d78590701874216be506ccc86973f3110ecae886d03e346f525de271e987ed34", "fetched_at": "2026-08-29T11:31:39.756356+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/installation"}, {"content_hash": "79a1cd4a0b66c42ba2015a3944cb7c645f088ab5074d9af168ea599e5ef9a0fc", "fetched_at": "2026-08-29T11:31:39.759528+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/getting-started/quickstart"}, {"content_hash": "7a2da837c1cf304b9703fc170c2d591b9f35a1b368614f7034092428583f7f1e", "fetched_at": "2026-08-29T11:31:39.762177+00:00", "kind": "site_page", "missing": false, "url": "https://vllm-mlx.is-a.dev/development/documentation"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 19, "rhythm": 97}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 270, "days_push": 7, "days_rel": 21, "gap_med": 10.5, "n_releases_24m": 13}, "score": 82, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}