@ggerganov
We joined forces with NVIDIA to unlock high-speed AI inference on RTX AI PCs and DGX Spark using llama.cpp. The latest Ministral-3B models reach 385+ tok/s on @NVIDIA_AI_PC GeForce RTX 5090 systems. Blog: https://t.co/60yKKzNnoN
🐦 Twitter Post Details
Viewing enriched Twitter post
📊 Media Metadata
{
"media": [
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1995931445425271232/media_0.png",
"filename": "media_0.png"
}
],
"processed_at": "2026-03-09T00:23:00.265684",
"pipeline_version": "2.0"
}🔧 Raw API Response
{
"type": "tweet",
"id": "1995931445425271232",
"url": "https://x.com/ggerganov/status/1995931445425271232",
"twitterUrl": "https://twitter.com/ggerganov/status/1995931445425271232",
"text": "We joined forces with NVIDIA to unlock high-speed AI inference on RTX AI PCs and DGX Spark using llama.cpp. The latest Ministral-3B models reach 385+ tok/s on @NVIDIA_AI_PC GeForce RTX 5090 systems.\n\nBlog: https://t.co/60yKKzNnoN",
"source": "Twitter for iPhone",
"retweetCount": 43,
"replyCount": 16,
"likeCount": 426,
"quoteCount": 10,
"viewCount": 32329,
"createdAt": "Tue Dec 02 19:01:53 +0000 2025",
"lang": "en",
"bookmarkCount": 80,
"isReply": false,
"inReplyToId": null,
"conversationId": "1995931445425271232",
"displayTextRange": [
0,
229
],
"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": 54047,
"following": 290,
"status": "",
"canDm": true,
"canMediaTag": false,
"createdAt": "Wed May 27 12:56:54 +0000 2015",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 3125,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 295,
"statusesCount": 1676,
"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": {
"binding_values": [
{
"key": "photo_image_full_size_large",
"value": {
"image_value": {
"height": 419,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=jpg&name=800x419",
"width": 800
}
}
},
{
"key": "thumbnail_image",
"value": {
"image_value": {
"height": 150,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=jpg&name=280x150",
"width": 266
}
}
},
{
"key": "description",
"value": {
"string_value": "The new Mistral 3 open model family delivers industry-leading accuracy, efficiency, and customization capabilities for developers and enterprises. Optimized from NVIDIA GB200 NVL72 to edge platforms…"
}
},
{
"key": "domain",
"value": {
"string_value": "developer.nvidia.com"
}
},
{
"key": "thumbnail_image_large",
"value": {
"image_value": {
"height": 320,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=jpg&name=800x320_1",
"width": 568
}
}
},
{
"key": "summary_photo_image_small",
"value": {
"image_value": {
"height": 202,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=jpg&name=386x202",
"width": 386
}
}
},
{
"key": "thumbnail_image_original",
"value": {
"image_value": {
"height": 527,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=jpg&name=orig",
"width": 936
}
}
},
{
"key": "photo_image_full_size_small",
"value": {
"image_value": {
"height": 202,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=jpg&name=386x202",
"width": 386
}
}
},
{
"key": "summary_photo_image_large",
"value": {
"image_value": {
"height": 419,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=jpg&name=800x419",
"width": 800
}
}
},
{
"key": "thumbnail_image_small",
"value": {
"image_value": {
"height": 81,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=jpg&name=144x144",
"width": 144
}
}
},
{
"key": "thumbnail_image_x_large",
"value": {
"image_value": {
"height": 527,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=png&name=2048x2048_2_exp",
"width": 936
}
}
},
{
"key": "photo_image_full_size_original",
"value": {
"image_value": {
"height": 527,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=jpg&name=orig",
"width": 936
}
}
},
{
"key": "vanity_url",
"value": {
"scribe_key": "vanity_url",
"string_value": "developer.nvidia.com"
}
},
{
"key": "photo_image_full_size",
"value": {
"image_value": {
"height": 314,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=jpg&name=600x314",
"width": 600
}
}
},
{
"key": "thumbnail_image_color",
"value": {
"image_color_value": {
"palette": [
{
"percentage": 96.09,
"rgb": {
"blue": 0,
"green": 0,
"red": 0
}
},
{
"percentage": 1.36,
"rgb": {
"blue": 199,
"green": 199,
"red": 199
}
},
{
"percentage": 0.69,
"rgb": {
"blue": 22,
"green": 141,
"red": 89
}
},
{
"percentage": 0.4,
"rgb": {
"blue": 11,
"green": 77,
"red": 49
}
},
{
"percentage": 0.15,
"rgb": {
"blue": 30,
"green": 106,
"red": 216
}
}
]
}
}
},
{
"key": "title",
"value": {
"string_value": "NVIDIA-Accelerated Mistral 3 Open Models Deliver Efficiency, Accuracy at Any Scale | NVIDIA..."
}
},
{
"key": "summary_photo_image_color",
"value": {
"image_color_value": {
"palette": [
{
"percentage": 96.09,
"rgb": {
"blue": 0,
"green": 0,
"red": 0
}
},
{
"percentage": 1.36,
"rgb": {
"blue": 199,
"green": 199,
"red": 199
}
},
{
"percentage": 0.69,
"rgb": {
"blue": 22,
"green": 141,
"red": 89
}
},
{
"percentage": 0.4,
"rgb": {
"blue": 11,
"green": 77,
"red": 49
}
},
{
"percentage": 0.15,
"rgb": {
"blue": 30,
"green": 106,
"red": 216
}
}
]
}
}
},
{
"key": "summary_photo_image_x_large",
"value": {
"image_value": {
"height": 527,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=png&name=2048x2048_2_exp",
"width": 936
}
}
},
{
"key": "summary_photo_image",
"value": {
"image_value": {
"height": 314,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=jpg&name=600x314",
"width": 600
}
}
},
{
"key": "photo_image_full_size_color",
"value": {
"image_color_value": {
"palette": [
{
"percentage": 96.09,
"rgb": {
"blue": 0,
"green": 0,
"red": 0
}
},
{
"percentage": 1.36,
"rgb": {
"blue": 199,
"green": 199,
"red": 199
}
},
{
"percentage": 0.69,
"rgb": {
"blue": 22,
"green": 141,
"red": 89
}
},
{
"percentage": 0.4,
"rgb": {
"blue": 11,
"green": 77,
"red": 49
}
},
{
"percentage": 0.15,
"rgb": {
"blue": 30,
"green": 106,
"red": 216
}
}
]
}
}
},
{
"key": "photo_image_full_size_x_large",
"value": {
"image_value": {
"height": 527,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=png&name=2048x2048_2_exp",
"width": 936
}
}
},
{
"key": "card_url",
"value": {
"scribe_key": "card_url",
"string_value": "https://t.co/60yKKzNnoN"
}
},
{
"key": "summary_photo_image_original",
"value": {
"image_value": {
"height": 527,
"url": "https://pbs.twimg.com/card_img/2028918984284758019/a_CJgP_c?format=jpg&name=orig",
"width": 936
}
}
}
],
"card_platform": {
"platform": {
"audience": {
"name": "production"
},
"device": {
"name": "iPhone",
"version": "13"
}
}
},
"name": "summary_large_image",
"url": "https://t.co/60yKKzNnoN",
"user_refs_results": []
},
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [
{
"display_url": "developer.nvidia.com/blog/nvidia-ac…",
"expanded_url": "https://developer.nvidia.com/blog/nvidia-accelerated-mistral-3-open-models-deliver-efficiency-accuracy-at-any-scale/",
"indices": [
206,
229
],
"url": "https://t.co/60yKKzNnoN"
}
],
"user_mentions": [
{
"id_str": "1853898859455348736",
"indices": [
159,
172
],
"name": "NVIDIA AI PC",
"screen_name": "NVIDIA_AI_PC"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
}