๐Ÿฆ Twitter Post Details

Viewing enriched Twitter post

@liquidai

Introducing LFM2.5-230M: our smallest model yet, built to run fast anywhere (CPUs, NPUs, and GPUs) to enable agentic tasks on phones, robots, home and network automation devices. > 230M parameters, built on the LFM2 architecture > Pre-trained on 19T tokens, with a 32K context extension > Post-trained with distillation from LFM2.5-350M > 213 tok/s decode speed on Galaxy S25 Ultra (CPU) > 42 tok/s on a Raspberry Pi 5 (CPU) > Competes with and often beats models more than twice its size on instruction following, data extraction, and tool use. > use it for large-scale data extraction pipelines or lightweight on-device agentic workloads. ๐Ÿงต

Media 1

๐Ÿ“Š Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2070148140368318884/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2070148140368318884/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-06-29T15:19:18.673508",
  "pipeline_version": "2.0"
}

๐Ÿ”ง Raw API Response

{
  "type": "tweet",
  "id": "2070148140368318884",
  "url": "https://x.com/liquidai/status/2070148140368318884",
  "twitterUrl": "https://twitter.com/liquidai/status/2070148140368318884",
  "text": "Introducing LFM2.5-230M: our smallest model yet, built to run fast anywhere (CPUs, NPUs, and GPUs) to enable agentic tasks on phones, robots, home and network automation devices. \n\n> 230M parameters, built on the LFM2 architecture\n> Pre-trained on 19T tokens, with a 32K context extension\n> Post-trained with distillation from LFM2.5-350M\n> 213 tok/s decode speed on Galaxy S25 Ultra (CPU)\n> 42 tok/s on a Raspberry Pi 5 (CPU) \n> Competes with and often beats models more than twice its size on instruction following, data extraction, and tool use.\n> use it for large-scale data extraction pipelines or lightweight on-device agentic workloads.\n\n๐Ÿงต",
  "source": "Twitter for iPhone",
  "retweetCount": 195,
  "replyCount": 81,
  "likeCount": 1889,
  "quoteCount": 78,
  "viewCount": 232004,
  "createdAt": "Thu Jun 25 14:12:32 +0000 2026",
  "lang": "en",
  "bookmarkCount": 1017,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2070148140368318884",
  "displayTextRange": [
    0,
    284
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "liquidai",
    "url": "https://x.com/liquidai",
    "twitterUrl": "https://twitter.com/liquidai",
    "id": "1635809139808141320",
    "name": "Liquid AI",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": "Business",
    "profilePicture": "https://pbs.twimg.com/profile_images/1702611993327251456/PUUuOA4W_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1635809139808141320/1766688037",
    "description": "",
    "location": "Cambridge, MA",
    "followers": 30826,
    "following": 44,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Wed Mar 15 01:04:36 +0000 2023",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 1561,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 167,
    "statusesCount": 685,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2060023455290974474"
    ],
    "profile_bio": {
      "description": "Build efficient general-purpose AI at every scale.",
      "entities": {
        "description": {},
        "url": {
          "urls": [
            {
              "display_url": "liquid.ai",
              "expanded_url": "https://www.liquid.ai",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/KwQwvrNUYn"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/Hmq5qAqcIs",
        "expanded_url": "https://twitter.com/liquidai/status/2070148140368318884/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2070148137079947264",
        "indices": [
          285,
          308
        ],
        "media_key": "3_2070148137079947264",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARy6pMM3FkAACgACHLqkw/sW0aQAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHLqkwzcWQAAKAAIcuqTD+xbRpAAA",
            "media_key": "3_2070148137079947264"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HLqkwzcWQAAMuIh.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 672,
              "w": 1200,
              "x": 0,
              "y": 0
            },
            {
              "h": 806,
              "w": 806,
              "x": 106,
              "y": 0
            },
            {
              "h": 806,
              "w": 707,
              "x": 156,
              "y": 0
            },
            {
              "h": 806,
              "w": 403,
              "x": 308,
              "y": 0
            },
            {
              "h": 806,
              "w": 1200,
              "x": 0,
              "y": 0
            }
          ],
          "height": 806,
          "width": 1200
        },
        "sizes": {
          "large": {
            "h": 806,
            "w": 1200
          }
        },
        "type": "photo",
        "url": "https://t.co/Hmq5qAqcIs"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}