🐦 Twitter Post Details

Viewing enriched Twitter post

@ai_fast_track

RT @kunal732: Introducing MLX-Swift-TS https://t.co/TDCJXVpago An SDK for running time series foundation models fully on-device on Apple Silicon. When I joined @datadoghq , I was introduced to Toto, our time series foundation model, and got excited about zero-shot forecasting across different domains. While building a health copilot app, I realized there wasn’t a simple way to run models like these locally on device. So I built one. MLX-Swift-TS exposes a common TimeSeriesForecaster interface for loading and running multiple time series architectures directly in Swift using MLX. No server required. The attached video shows on-device forecasting running inside a native Swift app. Huge thanks to @awnihannun and the MLX team for building MLX and its Swift API, @Prince_Canuma for inspiration on MLX SDK patterns, and @atalwalkar and the Datadog team for Toto.

Media 1
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2027280989110563134/media_0.jpg?",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-03-01T19:19:22.026407",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2027280989110563134",
  "url": "https://x.com/ai_fast_track/status/2027280989110563134",
  "twitterUrl": "https://twitter.com/ai_fast_track/status/2027280989110563134",
  "text": "RT @kunal732: Introducing MLX-Swift-TS\n https://t.co/9qmyqyISf6\nAn SDK for running time series foundation models fully on-device on Apple S…",
  "source": "Twitter for iPhone",
  "retweetCount": 8,
  "replyCount": 2,
  "likeCount": 89,
  "quoteCount": 1,
  "viewCount": 12156,
  "createdAt": "Fri Feb 27 07:13:47 +0000 2026",
  "lang": "en",
  "bookmarkCount": 75,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2027280989110563134",
  "displayTextRange": [
    0,
    140
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "ai_fast_track",
    "url": "https://x.com/ai_fast_track",
    "twitterUrl": "https://twitter.com/ai_fast_track",
    "id": "1214567550891298816",
    "name": "Farid",
    "isVerified": false,
    "isBlueVerified": false,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1559210322807881736/21bYos8e_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1214567550891298816/1660579647",
    "description": "",
    "location": "Montreal 🇨🇦",
    "followers": 5584,
    "following": 1339,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Tue Jan 07 15:20:56 +0000 2020",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 6203,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 381,
    "statusesCount": 3626,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "1583125709685673985"
    ],
    "profile_bio": {
      "description": "🚀 Mentor | IceVision Creator\n\n✨I help companies leverage AI and develop innovative products\n🧩I assist mentees in becoming the top 1% of AI practitioners",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [],
          "user_mentions": []
        },
        "url": {
          "urls": [
            {
              "display_url": "fastpath.one",
              "expanded_url": "https://www.fastpath.one",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/XMih9mtOCF"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "timestamps": [],
    "urls": [
      {
        "display_url": "github.com/kunal732/MLX-S…",
        "expanded_url": "https://github.com/kunal732/MLX-Swift-TS",
        "indices": [
          40,
          63
        ],
        "url": "https://t.co/9qmyqyISf6"
      }
    ],
    "user_mentions": [
      {
        "id_str": "24736711",
        "indices": [
          3,
          12
        ],
        "name": "Kunal Batra",
        "screen_name": "kunal732"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": {
    "type": "tweet",
    "id": "2026799368653643778",
    "url": "https://x.com/kunal732/status/2026799368653643778",
    "twitterUrl": "https://twitter.com/kunal732/status/2026799368653643778",
    "text": "Introducing MLX-Swift-TS\n https://t.co/TDCJXVpago\nAn SDK for running time series foundation models fully on-device on Apple Silicon.\n\nWhen I joined @datadoghq , I was introduced to Toto, our time series foundation model, and got excited about zero-shot forecasting across different domains. While building a health copilot app, I realized there wasn’t a simple way to run models like these locally on device. So I built one.\n\nMLX-Swift-TS exposes a common TimeSeriesForecaster interface for loading and running multiple time series architectures directly in Swift using MLX. No server required.\n\nThe attached video shows on-device forecasting running inside a native Swift app.\n\nHuge thanks to @awnihannun and the MLX team for building MLX and its Swift API, @Prince_Canuma for inspiration on MLX SDK patterns, and @atalwalkar and the Datadog team for Toto.",
    "source": "Twitter for iPhone",
    "retweetCount": 8,
    "replyCount": 2,
    "likeCount": 89,
    "quoteCount": 1,
    "viewCount": 12156,
    "createdAt": "Wed Feb 25 23:20:00 +0000 2026",
    "lang": "en",
    "bookmarkCount": 75,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2026799368653643778",
    "displayTextRange": [
      0,
      271
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "kunal732",
      "url": "https://x.com/kunal732",
      "twitterUrl": "https://twitter.com/kunal732",
      "id": "24736711",
      "name": "Kunal Batra",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": null,
      "profilePicture": "https://pbs.twimg.com/profile_images/731984377731809280/b_DKb702_normal.jpg",
      "coverPicture": "https://pbs.twimg.com/profile_banners/24736711/1554426590",
      "description": "",
      "location": "New York, NY",
      "followers": 1808,
      "following": 2375,
      "status": "",
      "canDm": true,
      "canMediaTag": true,
      "createdAt": "Mon Mar 16 18:01:46 +0000 2009",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 7902,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 380,
      "statusesCount": 2670,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [],
      "profile_bio": {
        "description": "Developer Relations @Datadoghq. Previously @AWS, @Clarifai, @Auth0, @SendGrid Opinions are my own.",
        "entities": {
          "description": {
            "hashtags": [],
            "symbols": [],
            "urls": [],
            "user_mentions": [
              {
                "id_str": "0",
                "indices": [
                  20,
                  30
                ],
                "name": "",
                "screen_name": "Datadoghq"
              },
              {
                "id_str": "0",
                "indices": [
                  43,
                  47
                ],
                "name": "",
                "screen_name": "AWS"
              },
              {
                "id_str": "0",
                "indices": [
                  49,
                  58
                ],
                "name": "",
                "screen_name": "Clarifai"
              },
              {
                "id_str": "0",
                "indices": [
                  60,
                  66
                ],
                "name": "",
                "screen_name": "Auth0"
              },
              {
                "id_str": "0",
                "indices": [
                  68,
                  77
                ],
                "name": "",
                "screen_name": "SendGrid"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {
      "media": [
        {
          "additional_media_info": {
            "monetizable": false
          },
          "display_url": "pic.twitter.com/7W3GPmEwDq",
          "expanded_url": "https://twitter.com/kunal732/status/2026799368653643778/video/1",
          "ext_media_availability": {
            "status": "Available"
          },
          "id_str": "2026798743933124608",
          "indices": [
            272,
            295
          ],
          "media_key": "13_2026798743933124608",
          "media_results": {
            "id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAARwgorgbV4AAAAA=",
            "result": {
              "__typename": "ApiMedia",
              "id": "QXBpTWVkaWE6DAAECgABHCCiuBtXgAAAAA==",
              "media_key": "13_2026798743933124608"
            }
          },
          "media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2026798743933124608/img/ceO6yuTYrkt4v1QK.jpg",
          "original_info": {
            "focus_rects": [],
            "height": 1388,
            "width": 3016
          },
          "sizes": {
            "large": {
              "h": 943,
              "w": 2048
            }
          },
          "type": "video",
          "url": "https://t.co/7W3GPmEwDq",
          "video_info": {
            "aspect_ratio": [
              754,
              347
            ],
            "duration_millis": 17100,
            "variants": [
              {
                "content_type": "application/x-mpegURL",
                "url": "https://video.twimg.com/amplify_video/2026798743933124608/pl/8dm2j5mQPPQprxA6.m3u8?tag=21"
              },
              {
                "bitrate": 256000,
                "content_type": "video/mp4",
                "url": "https://video.twimg.com/amplify_video/2026798743933124608/vid/avc1/586x270/LwrhROY8AP2vZaO8.mp4?tag=21"
              },
              {
                "bitrate": 832000,
                "content_type": "video/mp4",
                "url": "https://video.twimg.com/amplify_video/2026798743933124608/vid/avc1/782x360/e9Ldx--PmUs5ZHxQ.mp4?tag=21"
              },
              {
                "bitrate": 2176000,
                "content_type": "video/mp4",
                "url": "https://video.twimg.com/amplify_video/2026798743933124608/vid/avc1/1564x720/DmGWucVKVYsLvJwZ.mp4?tag=21"
              },
              {
                "bitrate": 10368000,
                "content_type": "video/mp4",
                "url": "https://video.twimg.com/amplify_video/2026798743933124608/vid/avc1/3016x1388/xJAnzPeBD55OsJGj.mp4?tag=21"
              }
            ]
          }
        }
      ]
    },
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "timestamps": [],
      "urls": [
        {
          "display_url": "github.com/kunal732/MLX-S…",
          "expanded_url": "https://github.com/kunal732/MLX-Swift-TS",
          "indices": [
            26,
            49
          ],
          "url": "https://t.co/TDCJXVpago"
        }
      ],
      "user_mentions": [
        {
          "id_str": "123093566",
          "indices": [
            148,
            158
          ],
          "name": "Datadog, Inc.",
          "screen_name": "datadoghq"
        },
        {
          "id_str": "245262377",
          "indices": [
            694,
            705
          ],
          "name": "Awni Hannun",
          "screen_name": "awnihannun"
        },
        {
          "id_str": "726009698",
          "indices": [
            759,
            773
          ],
          "name": "Prince Canuma",
          "screen_name": "Prince_Canuma"
        },
        {
          "id_str": "201811433",
          "indices": [
            815,
            826
          ],
          "name": "Ameet Talwalkar",
          "screen_name": "atalwalkar"
        }
      ]
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "article": null
  },
  "isLimitedReply": false,
  "article": null
}