🐦 Twitter Post Details

Viewing enriched Twitter post

@vllm_project

🎉 Congrats to @nvidia on the release of Nemotron 3 Super — day-0 support in vLLM v0.17.1! Verified on NVIDIA GPUs. 120B hybrid MoE, only 12B active at inference. Big upgrades over the previous Nemotron Super: - 5x higher throughput - 2x higher accuracy on Artificial Analysis Intelligence Index - Multi-Token Prediction (MTP) for faster long-form generation - Configurable thinking budget — dial accuracy vs token cost per task - 1M token context window Supports BF16, FP8, and NVFP4. Fully open: weights, datasets, recipes. Blog: https://t.co/PAN0y778iB 🤝 Thanks @NVIDIAAIDev Nemotron team and vLLM community contributors!

Media 1
Media 2
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2031779213527957732/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2031779213527957732/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2031779213527957732/media_1.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2031779213527957732/media_1.jpg",
      "type": "photo",
      "filename": "media_1.jpg"
    }
  ],
  "processed_at": "2026-03-13T01:21:26.942889",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2031779213527957732",
  "url": "https://x.com/vllm_project/status/2031779213527957732",
  "twitterUrl": "https://twitter.com/vllm_project/status/2031779213527957732",
  "text": "🎉 Congrats to @nvidia on the release of Nemotron 3 Super — day-0 support in vLLM v0.17.1! Verified on NVIDIA GPUs.\n\n120B hybrid MoE, only 12B active at inference. Big upgrades over the previous Nemotron Super:\n- 5x higher throughput\n- 2x higher accuracy on Artificial Analysis Intelligence Index\n- Multi-Token Prediction (MTP) for faster long-form generation\n- Configurable thinking budget — dial accuracy vs token cost per task\n- 1M token context window\n\nSupports BF16, FP8, and NVFP4. Fully open: weights, datasets, recipes.\n\nBlog: https://t.co/PAN0y778iB\n\n🤝 Thanks @NVIDIAAIDev Nemotron team and vLLM community contributors!",
  "source": "Twitter for iPhone",
  "retweetCount": 28,
  "replyCount": 9,
  "likeCount": 272,
  "quoteCount": 3,
  "viewCount": 26237,
  "createdAt": "Wed Mar 11 17:08:07 +0000 2026",
  "lang": "en",
  "bookmarkCount": 49,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2031779213527957732",
  "displayTextRange": [
    0,
    276
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "vllm_project",
    "url": "https://x.com/vllm_project",
    "twitterUrl": "https://twitter.com/vllm_project",
    "id": "1774187564276289536",
    "name": "vLLM",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1774187681746182144/N_5NJ8B1_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1774187564276289536/1733806062",
    "description": "",
    "location": "",
    "followers": 33294,
    "following": 32,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Sat Mar 30 21:31:01 +0000 2024",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 552,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 234,
    "statusesCount": 860,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [],
    "profile_bio": {
      "description": "A high-throughput and memory-efficient inference and serving engine for LLMs. Join https://t.co/lxJ0SfX5pJ to discuss together with the community!",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [
            {
              "display_url": "slack.vllm.ai",
              "expanded_url": "http://slack.vllm.ai",
              "indices": [
                83,
                106
              ],
              "url": "https://t.co/lxJ0SfX5pJ"
            }
          ],
          "user_mentions": []
        },
        "url": {
          "urls": [
            {
              "display_url": "vllm.ai",
              "expanded_url": "https://vllm.ai",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/OSHR5C6pCV"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/Vg1YoOd9W1",
        "expanded_url": "https://twitter.com/vllm_project/status/2031779213527957732/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2031779100046790656",
        "indices": [
          277,
          300
        ],
        "media_key": "3_2031779100046790656",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARwyVFOgWhAACgACHDJUbgxbQOQAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHDJUU6BaEAAKAAIcMlRuDFtA5AAA",
            "media_key": "3_2031779100046790656"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HDJUU6BaEAA8Icj.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 686,
              "w": 1225,
              "x": 0,
              "y": 0
            },
            {
              "h": 686,
              "w": 686,
              "x": 0,
              "y": 0
            },
            {
              "h": 686,
              "w": 602,
              "x": 38,
              "y": 0
            },
            {
              "h": 686,
              "w": 343,
              "x": 168,
              "y": 0
            },
            {
              "h": 686,
              "w": 1950,
              "x": 0,
              "y": 0
            }
          ],
          "height": 686,
          "width": 1950
        },
        "sizes": {
          "large": {
            "h": 686,
            "w": 1950
          }
        },
        "type": "photo",
        "url": "https://t.co/Vg1YoOd9W1"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "vllm.ai/blog/nemotron-…",
        "expanded_url": "https://vllm.ai/blog/nemotron-3-super",
        "indices": [
          534,
          557
        ],
        "url": "https://t.co/PAN0y778iB"
      }
    ],
    "user_mentions": [
      {
        "id_str": "61559439",
        "indices": [
          14,
          21
        ],
        "name": "NVIDIA",
        "screen_name": "nvidia"
      },
      {
        "id_str": "877952584333410305",
        "indices": [
          568,
          580
        ],
        "name": "NVIDIA AI Developer",
        "screen_name": "NVIDIAAIDev"
      }
    ]
  },
  "quoted_tweet": {
    "type": "tweet",
    "id": "2031774913544016179",
    "url": "https://x.com/NVIDIAAIDev/status/2031774913544016179",
    "twitterUrl": "https://twitter.com/NVIDIAAIDev/status/2031774913544016179",
    "text": "Introducing NVIDIA Nemotron 3 Super 🎉\n\nOpen 120B-parameter (12B active) hybrid Mamba-Transformer MoE model \n\nNative 1M-token context \n\nBuilt for compute-efficient, high-accuracy multi-agent applications\n\nPlus, fully open weights, datasets and recipes for easy customization and deployment. 🧵",
    "source": "Twitter for iPhone",
    "retweetCount": 101,
    "replyCount": 54,
    "likeCount": 777,
    "quoteCount": 32,
    "viewCount": 101284,
    "createdAt": "Wed Mar 11 16:51:02 +0000 2026",
    "lang": "en",
    "bookmarkCount": 238,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2031774913544016179",
    "displayTextRange": [
      0,
      277
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "NVIDIAAIDev",
      "url": "https://x.com/NVIDIAAIDev",
      "twitterUrl": "https://twitter.com/NVIDIAAIDev",
      "id": "877952584333410305",
      "name": "NVIDIA AI Developer",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": "Business",
      "profilePicture": "https://pbs.twimg.com/profile_images/1836133629694742531/verSRYr8_normal.jpg",
      "coverPicture": "https://pbs.twimg.com/profile_banners/877952584333410305/1753484171",
      "description": "",
      "location": "Santa Clara, CA",
      "followers": 95931,
      "following": 363,
      "status": "",
      "canDm": false,
      "canMediaTag": true,
      "createdAt": "Thu Jun 22 18:13:02 +0000 2017",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 8550,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 3043,
      "statusesCount": 6908,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [
        "2031774913544016179"
      ],
      "profile_bio": {
        "description": "All things AI for developers from @NVIDIA.",
        "entities": {
          "description": {
            "hashtags": [],
            "symbols": [],
            "urls": [],
            "user_mentions": [
              {
                "id_str": "0",
                "indices": [
                  34,
                  41
                ],
                "name": "",
                "screen_name": "NVIDIA"
              }
            ]
          },
          "url": {
            "urls": [
              {
                "display_url": "developer.nvidia.com/blog",
                "expanded_url": "https://developer.nvidia.com/blog",
                "indices": [
                  0,
                  23
                ],
                "url": "https://t.co/WjFyGBCF6Q"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {
      "media": [
        {
          "additional_media_info": {
            "monetizable": false
          },
          "display_url": "pic.twitter.com/kMFI23noFc",
          "expanded_url": "https://twitter.com/NVIDIAAIDev/status/2031774913544016179/video/1",
          "ext_media_availability": {
            "status": "Available"
          },
          "id_str": "2031774841355841536",
          "indices": [
            278,
            301
          ],
          "media_key": "13_2031774841355841536",
          "media_results": {
            "id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAARwyUHQSlzAAAAA=",
            "result": {
              "__typename": "ApiMedia",
              "id": "QXBpTWVkaWE6DAAECgABHDJQdBKXMAAAAA==",
              "media_key": "13_2031774841355841536"
            }
          },
          "media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2031774841355841536/img/tpUBoaN5AgVAbm3h.jpg",
          "original_info": {
            "focus_rects": [],
            "height": 1350,
            "width": 1080
          },
          "sizes": {
            "large": {
              "h": 1350,
              "w": 1080
            }
          },
          "type": "video",
          "url": "https://t.co/kMFI23noFc",
          "video_info": {
            "aspect_ratio": [
              4,
              5
            ],
            "duration_millis": 93616,
            "variants": [
              {
                "content_type": "application/x-mpegURL",
                "url": "https://video.twimg.com/amplify_video/2031774841355841536/pl/CLbJFFKkw0nEGtkI.m3u8?tag=14&v=d13"
              },
              {
                "bitrate": 632000,
                "content_type": "video/mp4",
                "url": "https://video.twimg.com/amplify_video/2031774841355841536/vid/avc1/320x400/mJz2Qjag6BC3Fjw0.mp4?tag=14"
              },
              {
                "bitrate": 950000,
                "content_type": "video/mp4",
                "url": "https://video.twimg.com/amplify_video/2031774841355841536/vid/avc1/480x600/H_OuLz3B03RCsMz2.mp4?tag=14"
              },
              {
                "bitrate": 2176000,
                "content_type": "video/mp4",
                "url": "https://video.twimg.com/amplify_video/2031774841355841536/vid/avc1/720x900/bBTeoagNeGOLjqly.mp4?tag=14"
              }
            ]
          }
        }
      ]
    },
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "timestamps": [],
      "urls": [],
      "user_mentions": []
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "article": null
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}