@JohnMai_Dev
I just implemented inference for Qwen3.5 0.8B based on https://t.co/W8bSA5TRiO, and successfully ran it on an M1 Pro. https://t.co/z0g1ynNlq3
Viewing enriched Twitter post
I just implemented inference for Qwen3.5 0.8B based on https://t.co/W8bSA5TRiO, and successfully ran it on an M1 Pro. https://t.co/z0g1ynNlq3
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2028794989069881465/media_0.jpg?",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2028794989069881465/media_0.jpg?",
"type": "photo",
"filename": "media_0.jpg"
},
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2028794989069881465/media_1.mp4?",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2028794989069881465/media_1.mp4?",
"type": "video",
"filename": "media_1.mp4"
},
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2028794989069881465/media_2.jpg?",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2028794989069881465/media_2.jpg?",
"type": "photo",
"filename": "media_2.jpg"
}
],
"processed_at": "2026-03-06T14:11:17.494103",
"pipeline_version": "2.0"
} {
"type": "tweet",
"id": "2028794989069881465",
"url": "https://x.com/JohnMai_Dev/status/2028794989069881465",
"twitterUrl": "https://twitter.com/JohnMai_Dev/status/2028794989069881465",
"text": "I just implemented inference for Qwen3.5 0.8B based on https://t.co/W8bSA5TRiO, and successfully ran it on an M1 Pro. https://t.co/z0g1ynNlq3",
"source": "Twitter for iPhone",
"retweetCount": 159,
"replyCount": 65,
"likeCount": 1758,
"quoteCount": 22,
"viewCount": 246456,
"createdAt": "Tue Mar 03 11:29:53 +0000 2026",
"lang": "en",
"bookmarkCount": 1442,
"isReply": false,
"inReplyToId": null,
"conversationId": "2028794989069881465",
"displayTextRange": [
0,
117
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "JohnMai_Dev",
"url": "https://x.com/JohnMai_Dev",
"twitterUrl": "https://twitter.com/JohnMai_Dev",
"id": "1075346769741922304",
"name": "John Mai",
"isVerified": false,
"isBlueVerified": false,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1765025742008864768/eXj--qk7_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1075346769741922304/1545241746",
"description": "",
"location": "",
"followers": 1438,
"following": 3529,
"status": "",
"canDm": true,
"canMediaTag": false,
"createdAt": "Wed Dec 19 11:07:03 +0000 2018",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 8687,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 61,
"statusesCount": 392,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1970894975929131366"
],
"profile_bio": {
"description": "Full Stack/ML Research Engineer · Building ChatMLX|Go ORM Helper|swift-jinja · AI · LLM · MLX",
"entities": {
"description": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": []
},
"url": {
"urls": [
{
"display_url": "github.com/johnmai-dev",
"expanded_url": "https://github.com/johnmai-dev",
"indices": [
0,
23
],
"url": "https://t.co/r3VNgWzzSb"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"display_url": "pic.twitter.com/z0g1ynNlq3",
"expanded_url": "https://twitter.com/JohnMai_Dev/status/2028794989069881465/video/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": [
{
"h": 48,
"w": 48,
"x": 19,
"y": 196
},
{
"h": 38,
"w": 38,
"x": 266,
"y": 692
},
{
"h": 48,
"w": 48,
"x": 1,
"y": 401
}
]
},
"orig": {
"faces": [
{
"h": 48,
"w": 48,
"x": 19,
"y": 196
},
{
"h": 38,
"w": 38,
"x": 266,
"y": 692
},
{
"h": 48,
"w": 48,
"x": 1,
"y": 401
}
]
}
},
"id_str": "2028793364989333507",
"indices": [
118,
141
],
"media_key": "3_2028793364989333507",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARwnuNEC29ADCgACHCe6SyWaUHkAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHCe40QLb0AMKAAIcJ7pLJZpQeQAA",
"media_key": "3_2028793364989333507"
}
},
"media_url_https": "https://pbs.twimg.com/media/HCe40QLb0AMy9Kg.jpg",
"original_info": {
"focus_rects": [
{
"h": 449,
"w": 802,
"x": 0,
"y": 15
},
{
"h": 802,
"w": 802,
"x": 0,
"y": 0
},
{
"h": 914,
"w": 802,
"x": 0,
"y": 0
},
{
"h": 1064,
"w": 532,
"x": 270,
"y": 0
},
{
"h": 1064,
"w": 802,
"x": 0,
"y": 0
}
],
"height": 1064,
"width": 802
},
"sizes": {
"large": {
"h": 1064,
"w": 802
}
},
"type": "photo",
"url": "https://t.co/z0g1ynNlq3"
},
{
"additional_media_info": {
"monetizable": false
},
"display_url": "pic.twitter.com/z0g1ynNlq3",
"expanded_url": "https://twitter.com/JohnMai_Dev/status/2028794989069881465/video/1",
"ext_media_availability": {
"status": "Available"
},
"id_str": "2028793396685664256",
"indices": [
118,
141
],
"media_key": "13_2028793396685664256",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAARwnuNhkG3AAAAA=",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAAECgABHCe42GQbcAAAAA==",
"media_key": "13_2028793396685664256"
}
},
"media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2028793396685664256/img/vt4NDzUG7beDkDM6.jpg",
"original_info": {
"focus_rects": [],
"height": 1066,
"width": 814
},
"sizes": {
"large": {
"h": 1066,
"w": 814
}
},
"type": "video",
"url": "https://t.co/z0g1ynNlq3",
"video_info": {
"aspect_ratio": [
407,
533
],
"duration_millis": 14350,
"variants": [
{
"content_type": "application/x-mpegURL",
"url": "https://video.twimg.com/amplify_video/2028793396685664256/pl/SpN6GS7DTREin4mb.m3u8?tag=14"
},
{
"bitrate": 632000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2028793396685664256/vid/avc1/320x418/LRJMPsBNfNHsXEUz.mp4?tag=14"
},
{
"bitrate": 950000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2028793396685664256/vid/avc1/480x628/fdAQ6Z6bvs4j4zcP.mp4?tag=14"
},
{
"bitrate": 2176000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2028793396685664256/vid/avc1/720x942/E58kWMxKdDaDgFrL.mp4?tag=14"
}
]
}
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [
{
"display_url": "github.com/maderix/ANE",
"expanded_url": "https://github.com/maderix/ANE",
"indices": [
55,
78
],
"url": "https://t.co/W8bSA5TRiO"
}
],
"user_mentions": []
},
"quoted_tweet": {
"type": "tweet",
"id": "2028524908779802736",
"url": "https://x.com/BrianRoemmele/status/2028524908779802736",
"twitterUrl": "https://twitter.com/BrianRoemmele/status/2028524908779802736",
"text": "BOOM!\n\nApple’s Neural Engine Was Just Cracked Open, The Future of AI Training Just Change And Zero-Human Company Is Already Testing It!\n\nIn a jaw-dropping open-source breakthrough, a lone developer has done what Apple said was impossible: full neural network training– including backpropagation – directly on the Apple Neural Engine (ANE). No CoreML, no Metal, no GPU. Pure, blazing ANE silicon.\n\nThe project (https://t.co/jrk67hf9p1) delivers a single transformer layer (dim=768, seq=512) in just 9.3 ms per step at 1.78 TFLOPS sustained with only 11.2% ANE utilization on an M4 chip. That’s the same idle chip sitting in millions of Mac minis, MacBooks, and iMacs right now.\n\nTranslation? Your desktop just became a hyper-efficient AI supercomputer.\n\nThe numbers are insane: M4 ANE hits roughly 6.6 TFLOPS per watt – 80 times more efficient than an NVIDIA A100. Real-world throughput crushes Apple’s own “38 TOPS” marketing claims. And because it sips power like a phone, you can train 24/7 without melting your electricity bill or the planet.\n\nAt The Zero-Human Company, we’re not waiting. We are testing this right now on real ZHC workloads. This is the missing piece we’ve been chasing for our Zero Human Company vision: reviving archived data into fully autonomous AI systems with zero human overhead.\n\nThis is world-changing.\n\nFor the first time, anyone with a Mac can fine-tune, train, or iterate massive models locally, privately, and at a fraction of the cost of cloud GPUs. \n\nNo more renting $40,000 A100 clusters. No more waiting in queues. No more massive carbon footprints.\n\nTraining costs that used to run into the tens or hundreds of thousands of dollars? Plummeting toward pennies on the dollar – mostly just the electricity your Mac was already using while it sat idle.\n\nThe AI revolution just moved from billion-dollar data centers to your desk.\n\nWE WILL HAVE A NEW ZERO-HUMAN COMPANY @ HOME wage for equipped Macs that will be up to 100x more income for the owner! \n\nWe’re only at the beginning (single-layer today, full models tomorrow), but the door is wide open. Ultra-cheap, on-device training is here.\n\nThe future isn’t coming. It’s already running on your Mac.\n\nWelcome to the Zero-Human Company era.",
"source": "Twitter for iPhone",
"retweetCount": 1291,
"replyCount": 374,
"likeCount": 8625,
"quoteCount": 260,
"viewCount": 2020690,
"createdAt": "Mon Mar 02 17:36:41 +0000 2026",
"lang": "en",
"bookmarkCount": 11913,
"isReply": false,
"inReplyToId": null,
"conversationId": "2028524908779802736",
"displayTextRange": [
0,
278
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "BrianRoemmele",
"url": "https://x.com/BrianRoemmele",
"twitterUrl": "https://twitter.com/BrianRoemmele",
"id": "101584084",
"name": "Brian Roemmele",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1492616506/Brian-Med-Green-Fin_normal.png",
"coverPicture": "https://pbs.twimg.com/profile_banners/101584084/1414798559",
"description": "",
"location": "transcendence",
"followers": 457332,
"following": 42856,
"status": "",
"canDm": true,
"canMediaTag": false,
"createdAt": "Sun Jan 03 22:04:29 +0000 2010",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 639591,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 46012,
"statusesCount": 168309,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1564825039731535872"
],
"profile_bio": {
"description": "we can only see what we think is possible...",
"entities": {
"description": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": []
},
"url": {
"urls": [
{
"display_url": "readmultiplex.com",
"expanded_url": "http://readmultiplex.com/",
"indices": [
0,
23
],
"url": "https://t.co/riCFzsOQbj"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"allow_download_status": {
"allow_download": true
},
"display_url": "pic.twitter.com/maS3TQWO7S",
"expanded_url": "https://twitter.com/BrianRoemmele/status/2028524908779802736/photo/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": [
{
"h": 46,
"w": 46,
"x": 336,
"y": 976
}
]
},
"orig": {
"faces": [
{
"h": 46,
"w": 46,
"x": 336,
"y": 976
}
]
}
},
"id_str": "2028524904858185728",
"indices": [
279,
302
],
"media_key": "3_2028524904858185728",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARwmxKdEGvAACgACHCbEqC3aEHAAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHCbEp0Qa8AAKAAIcJsSoLdoQcAAA",
"media_key": "3_2028524904858185728"
}
},
"media_url_https": "https://pbs.twimg.com/media/HCbEp0Qa8AAX9we.jpg",
"original_info": {
"focus_rects": [
{
"h": 722,
"w": 1289,
"x": 0,
"y": 383
},
{
"h": 1105,
"w": 1105,
"x": 0,
"y": 0
},
{
"h": 1105,
"w": 969,
"x": 0,
"y": 0
},
{
"h": 1105,
"w": 553,
"x": 14,
"y": 0
},
{
"h": 1105,
"w": 1289,
"x": 0,
"y": 0
}
],
"height": 1105,
"width": 1289
},
"sizes": {
"large": {
"h": 1105,
"w": 1289
}
},
"type": "photo",
"url": "https://t.co/maS3TQWO7S"
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [
{
"display_url": "github.com/maderix/ANE",
"expanded_url": "http://github.com/maderix/ANE",
"indices": [
410,
433
],
"url": "https://t.co/jrk67hf9p1"
}
],
"user_mentions": []
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
}