@ggerganov
RT @ngxson: llama.cpp now supports various small OCR models that can run on low-end devices. These models are small enough to run on GPU wi…
Viewing enriched Twitter post
RT @ngxson: llama.cpp now supports various small OCR models that can run on low-end devices. These models are small enough to run on GPU wi…
{
"score": 0.34,
"score_components": {
"author": 0.09,
"engagement": 0.0,
"quality": 0.04000000000000001,
"source": 0.135,
"nlp": 0.05,
"recency": 0.025
},
"scored_at": "2026-04-11T22:23:09.045286",
"import_source": "api_import",
"source_tagged_at": "2026-04-11T22:23:09.045295",
"enriched": true,
"enriched_at": "2026-04-11T22:23:09.045296"
} {
"type": "tweet",
"id": "2042680998492569973",
"url": "https://x.com/ggerganov/status/2042680998492569973",
"twitterUrl": "https://twitter.com/ggerganov/status/2042680998492569973",
"text": "RT @ngxson: llama.cpp now supports various small OCR models that can run on low-end devices. These models are small enough to run on GPU wi…",
"source": "Twitter for iPhone",
"retweetCount": 24,
"replyCount": 9,
"likeCount": 236,
"quoteCount": 0,
"viewCount": 19977,
"createdAt": "Fri Apr 10 19:07:55 +0000 2026",
"lang": "en",
"bookmarkCount": 254,
"isReply": false,
"inReplyToId": null,
"conversationId": "2042680998492569973",
"displayTextRange": [
0,
140
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "ggerganov",
"url": "https://x.com/ggerganov",
"twitterUrl": "https://twitter.com/ggerganov",
"id": "3300401027",
"name": "Georgi Gerganov",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1654097134315098113/zCZD0wYz_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/3300401027/1716922617",
"description": "",
"location": "",
"followers": 57593,
"following": 290,
"status": "",
"canDm": true,
"canMediaTag": false,
"createdAt": "Wed May 27 12:56:54 +0000 2015",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 3172,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 305,
"statusesCount": 1712,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2024839991482777976"
],
"profile_bio": {
"description": "24th at the Electrica puzzle challenge | building https://t.co/baTQS2bdia | engineer @huggingface",
"entities": {
"description": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "github.com/ggml-org",
"expanded_url": "https://github.com/ggml-org",
"indices": [
50,
73
],
"url": "https://t.co/baTQS2bdia"
}
],
"user_mentions": [
{
"id_str": "0",
"indices": [
85,
97
],
"name": "",
"screen_name": "huggingface"
}
]
},
"url": {
"urls": [
{
"display_url": "github.com/ggerganov",
"expanded_url": "https://github.com/ggerganov",
"indices": [
0,
23
],
"url": "https://t.co/0H5L2twAKi"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "1293105854389133312",
"indices": [
3,
10
],
"name": "Xuan-Son Nguyen",
"screen_name": "ngxson"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": {
"type": "tweet",
"id": "2042631708650963344",
"url": "https://x.com/ngxson/status/2042631708650963344",
"twitterUrl": "https://twitter.com/ngxson/status/2042631708650963344",
"text": "llama.cpp now supports various small OCR models that can run on low-end devices. These models are small enough to run on GPU with 4GB VRAM, and some of them can even run on CPU with decent performance.\n\nIn this post, I will show you how to use these OCR models with llama.cpp 👇",
"source": "Twitter for iPhone",
"retweetCount": 24,
"replyCount": 9,
"likeCount": 236,
"quoteCount": 0,
"viewCount": 19977,
"createdAt": "Fri Apr 10 15:52:04 +0000 2026",
"lang": "en",
"bookmarkCount": 254,
"isReply": false,
"inReplyToId": null,
"conversationId": "2042631708650963344",
"displayTextRange": [
0,
277
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "ngxson",
"url": "https://x.com/ngxson",
"twitterUrl": "https://twitter.com/ngxson",
"id": "1293105854389133312",
"name": "Xuan-Son Nguyen",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1823412255280472064/VoZb_cia_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1293105854389133312/1741182277",
"description": "",
"location": "Paris",
"followers": 6281,
"following": 239,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Tue Aug 11 08:44:04 +0000 2020",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 1458,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 269,
"statusesCount": 1032,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2003077674496131118"
],
"profile_bio": {
"description": "Engineer @huggingface",
"entities": {
"description": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": [
{
"id_str": "0",
"indices": [
9,
21
],
"name": "",
"screen_name": "huggingface"
}
]
},
"url": {
"urls": [
{
"display_url": "ngxson.com",
"expanded_url": "https://ngxson.com",
"indices": [
0,
23
],
"url": "https://t.co/8kapnfl9di"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": []
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"isLimitedReply": false,
"communityInfo": null,
"article": null
}