🐦 Twitter Post Details

Viewing enriched Twitter post

@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 2

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2026799368653643778/media_0.mp4?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2026799368653643778/media_0.mp4?",
      "type": "video",
      "filename": "media_0.mp4"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2026799368653643778/media_1.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2026799368653643778/media_1.jpg?",
      "type": "photo",
      "filename": "media_1.jpg"
    }
  ],
  "processed_at": "2026-03-01T19:19:23.897188",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "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
}