{
  "type": "tweet",
  "id": "2070518167399698490",
  "url": "https://x.com/rasbt/status/2070518167399698490",
  "twitterUrl": "https://twitter.com/rasbt/status/2070518167399698490",
  "text": "Have been taking different local open-weight LLMs for a test drive in different harnesses (Qwen-Code, Codex, Claude Code).\n\n30B Mixture-of-Expert models are kind of a nice sweet spot and can solve challenging problems. And they get roughly 40 tok/sec on a Mac or DGX Spark, which is similar to GPT 5.5 in a Pro subscription and totally useable for everyday work.\n\nMore interesting is also the harness choice! Claude Code seems to be using 2x many tokens as Codex.\n\nGemma 4 E2B is here just for reference to show that the tasks can't be trivially solved by smaller models.\n\nJust finishing a longer write-up about this and will share soon (likely tomorrow)!",
  "source": "Twitter for iPhone",
  "retweetCount": 102,
  "replyCount": 105,
  "likeCount": 868,
  "quoteCount": 10,
  "viewCount": 56357,
  "createdAt": "Fri Jun 26 14:42:54 +0000 2026",
  "lang": "en",
  "bookmarkCount": 378,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2070518167399698490",
  "displayTextRange": [
    0,
    279
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "rasbt",
    "url": "https://x.com/rasbt",
    "twitterUrl": "https://twitter.com/rasbt",
    "id": "865622395",
    "name": "Sebastian Raschka",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1661187442043486209/a3E4t1eV_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/865622395/1742309979",
    "description": "",
    "location": "United States",
    "followers": 468902,
    "following": 1157,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Sun Oct 07 02:06:16 +0000 2012",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 25023,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 2133,
    "statusesCount": 19793,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2040423398824698310"
    ],
    "profile_bio": {
      "description": "ML/AI research engineer. Ex stats professor.\nAuthor of \"Build a Large Language Model From Scratch\" (https://t.co/O8LAAMRzzW) & reasoning (https://t.co/5TueQKx2Fk)",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "amzn.to/4fqvn0D",
              "expanded_url": "https://amzn.to/4fqvn0D",
              "indices": [
                100,
                123
              ],
              "url": "https://t.co/O8LAAMRzzW"
            },
            {
              "display_url": "mng.bz/lZ5B",
              "expanded_url": "https://mng.bz/lZ5B",
              "indices": [
                138,
                161
              ],
              "url": "https://t.co/5TueQKx2Fk"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "sebastianraschka.com",
              "expanded_url": "https://sebastianraschka.com",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/HrtQQ5tgJl"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/IT7d7djVy2",
        "expanded_url": "https://twitter.com/rasbt/status/2070518167399698490/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2070518149254987777",
        "indices": [
          280,
          303
        ],
        "media_key": "3_2070518149254987777",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARy79UljV8ABCgACHLv1TZzaEDoAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHLv1SWNXwAEKAAIcu/VNnNoQOgAA",
            "media_key": "3_2070518149254987777"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HLv1SWNXwAEb6dR.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 1398,
              "w": 2496,
              "x": 0,
              "y": 0
            },
            {
              "h": 1448,
              "w": 1448,
              "x": 0,
              "y": 0
            },
            {
              "h": 1448,
              "w": 1270,
              "x": 0,
              "y": 0
            },
            {
              "h": 1448,
              "w": 724,
              "x": 73,
              "y": 0
            },
            {
              "h": 1448,
              "w": 2496,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1448,
          "width": 2496
        },
        "sizes": {
          "large": {
            "h": 1188,
            "w": 2048
          }
        },
        "type": "photo",
        "url": "https://t.co/IT7d7djVy2"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}