@ggerganov
RT @alvarobartt: llama.cpp b11938 on M2 Pro 32 GiB (using ~3 GiB with the full 128K context) at ~110 t/s with c1 running with Pi! llama seβ¦
Viewing enriched Twitter post
RT @alvarobartt: llama.cpp b11938 on M2 Pro 32 GiB (using ~3 GiB with the full 128K context) at ~110 t/s with c1 running with Pi! llama seβ¦
{
"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": "2026-10-28T13:01:41.016249",
"import_source": "api_import",
"source_tagged_at": "2026-10-28T13:01:41.016261",
"enriched": true,
"enriched_at": "2026-10-28T13:01:41.016263"
} {
"type": "tweet",
"id": "2115423708194201738",
"url": "https://x.com/ggerganov/status/2115423708194201738",
"twitterUrl": "https://twitter.com/ggerganov/status/2115423708194201738",
"text": "RT @alvarobartt: llama.cpp b11938 on M2 Pro 32 GiB (using ~3 GiB with the full 128K context) at ~110 t/s with c1 running with Pi!\n\nllama seβ¦",
"source": "",
"retweetCount": 6,
"replyCount": 4,
"likeCount": 47,
"quoteCount": 2,
"viewCount": 2870,
"createdAt": "Wed Oct 28 12:41:29 +0000 2026",
"lang": "en",
"bookmarkCount": 17,
"isReply": false,
"inReplyToId": null,
"conversationId": "2115423708194201738",
"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/3300401027/1781278153",
"description": "",
"location": "",
"followers": 73548,
"following": 298,
"status": "",
"canDm": true,
"canMediaTag": false,
"createdAt": "Wed May 27 12:56:54 +0000 2015",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 3328,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 316,
"statusesCount": 1812,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [],
"profile_bio": {
"description": "24th at the Electrica puzzle challenge | building https://t.co/baTQS2bL7I | engineer @huggingface",
"entities": {
"description": {
"urls": [
{
"display_url": "github.com/ggml-org",
"expanded_url": "https://github.com/ggml-org",
"indices": [
50,
73
],
"url": "https://t.co/baTQS2bL7I"
}
],
"user_mentions": [
{
"id_str": "",
"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/0H5L2tx8zQ"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null,
"protected": false
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"user_mentions": [
{
"id_str": "1294542169357848576",
"indices": [
3,
15
],
"name": "Alvaro Bartolome",
"screen_name": "alvarobartt"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": {
"type": "tweet",
"id": "2115129281169006786",
"url": "https://x.com/alvarobartt/status/2115129281169006786",
"twitterUrl": "https://twitter.com/alvarobartt/status/2115129281169006786",
"text": "llama.cpp b11938 on M2 Pro 32 GiB (using ~3 GiB with the full 128K context) at ~110 t/s with c1 running with Pi!\n\nllama serve --hf-repo LiquidAI/LFM3-VL-2B-GGUF:Q4_K_M --host 0.0.0.0 --port 8080 -fa on -np 1 --top-p 1.0 --min-p 0.0 https://t.co/enITzfYaPQ",
"source": "",
"retweetCount": 6,
"replyCount": 4,
"likeCount": 47,
"quoteCount": 2,
"viewCount": 2870,
"createdAt": "Tue Oct 27 17:11:32 +0000 2026",
"lang": "en",
"bookmarkCount": 17,
"isReply": false,
"inReplyToId": null,
"conversationId": "2115129281169006786",
"displayTextRange": [
0,
231
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "alvarobartt",
"url": "https://x.com/alvarobartt",
"twitterUrl": "https://twitter.com/alvarobartt",
"id": "1294542169357848576",
"name": "Alvaro Bartolome",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/2052282525360242693/L12GieUi_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1294542169357848576/1774884851",
"description": "",
"location": "Valencia, Spain",
"followers": 2471,
"following": 432,
"status": "",
"canDm": true,
"canMediaTag": false,
"createdAt": "Sat Aug 15 07:51:27 +0000 2020",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 5296,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 290,
"statusesCount": 2284,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2115129281169006786"
],
"profile_bio": {
"description": "engineering @huggingface",
"entities": {
"description": {
"user_mentions": [
{
"id_str": "",
"indices": [
12,
24
],
"name": "",
"screen_name": "huggingface"
}
]
},
"url": {
"urls": [
{
"display_url": "alvarobartt.com",
"expanded_url": "https://alvarobartt.com",
"indices": [
0,
23
],
"url": "https://t.co/fxR2s3N9BF"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null,
"protected": false
},
"extendedEntities": {
"media": [
{
"additional_media_info": {
"monetizable": false
},
"allow_download_status": {
"allow_download": true
},
"display_url": "pic.x.com/enITzfYaPQ",
"expanded_url": "https://x.com/alvarobartt/status/2115129281169006786/video/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"features": {
"all": {
"tags": [
{
"name": "Llama App",
"screen_name": "llama_cpp",
"type": "user",
"user_id": "2090054405479387136"
},
{
"name": "Liquid AI",
"screen_name": "liquidai",
"type": "user",
"user_id": "1635809139808141320"
},
{
"name": "Pi",
"screen_name": "pidotdev",
"type": "user",
"user_id": "2056719344202141696"
}
]
}
},
"id_str": "2115129002171969536",
"indices": [
232,
255
],
"media_key": "13_2115129002171969536",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAAR1acp78ljAAAAA=",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAAECgABHVpynvyWMAAAAA==",
"media_key": "13_2115129002171969536"
}
},
"media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2115129002171969536/img/K2O26S59_oBYPqZ8.jpg",
"original_info": {
"focus_rects": [],
"height": 2160,
"width": 3396
},
"sizes": {
"large": {
"h": 1303,
"w": 2048
}
},
"type": "video",
"url": "https://t.co/enITzfYaPQ",
"video_info": {
"aspect_ratio": [
283,
180
],
"duration_millis": 77616,
"variants": [
{
"content_type": "application/x-mpegURL",
"url": "https://video-s.twimg.com/amplify_video/2115129002171969536/pl/xgfSJcMvSKiCMP3Z.m3u8?tag=29"
},
{
"bitrate": 256000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2115129002171969536/vid/avc1/424x270/fuh-GUu8Z8L61SJj.mp4?tag=29"
},
{
"bitrate": 832000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2115129002171969536/vid/avc1/566x360/-jxY1iT7cIANe88u.mp4?tag=29"
},
{
"bitrate": 2176000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2115129002171969536/vid/avc1/1132x720/0R0OqPrKMa1YIOoW.mp4?tag=29"
},
{
"bitrate": 10368000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2115129002171969536/vid/avc1/1698x1080/3K2I28SUs6WAJNML.mp4?tag=29"
},
{
"bitrate": 25128000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2115129002171969536/vid/avc1/3396x2160/IKHi47ssLrHmKVfi.mp4?tag=29"
}
]
}
}
]
},
"card": null,
"place": {},
"entities": {},
"quoted_tweet": {
"type": "tweet",
"id": "2115128329003303107",
"url": "https://x.com/liquidai/status/2115128329003303107",
"twitterUrl": "https://twitter.com/liquidai/status/2115128329003303107",
"text": "Introducing π»π΅πΌπΉ: our new generation of Liquid Foundation Models. With a new tri-hybrid architecture and new multimodal encoders, the LFM3 family is the ideal model suite for specialized intelligence.\n\n> 6 model instances, across text, audio, vision, and omni modalities, generative and decision models.\n> π»π΅πΌπΉ-π·.π½π±: text, 256k context window.\n> π»π΅πΌπΉ-π
π»-πΈπ±: vision-language model with video-input support for spatial understanding\n> π»π΅πΌπΉ-π°ππππ-πΈπ±: tool calls, voice chat, reasoning in 18 languages.\n> π»π΅πΌπΉ-πΎπππ-πΈπ±: an omni model combines vision, audio, and language.\n> ππ·-πΈπ± and ππ·-πΎπππ-πΈπ±: decision models with typed outputs and calibrated probabilities in a single pass. Omni adds audio input.\n> fine-tune on 1 GPU.\n> a new tri-hybrid architecture\n> architecture optimized for 14 processor classes across GPUs, CPUs, and NPUs.\n> π»π΅πΌπΉ-π
π»-πΈπ± is a beast. It performs competitively with Gemma 4 12B (6x larger), and Gemini 3.5 Flash Lite, and GPT-5.6 Luna, with 1.9B parameters.\n> π»π΅πΌπΉ-π·.π½π± is #1 on the Pareto frontier of device intelligence πππππππ.ππππππ.ππ\n\nEvery modality for specialized intelligence. Pick the one that fits your use case, customize it, and run it on-device.\n\n1/ π§΅",
"source": "",
"retweetCount": 3002,
"replyCount": 425,
"likeCount": 7488,
"quoteCount": 594,
"viewCount": 1478944,
"createdAt": "Tue Oct 27 17:07:45 +0000 2026",
"lang": "en",
"bookmarkCount": 7216,
"isReply": false,
"inReplyToId": null,
"conversationId": "2115128329003303107",
"displayTextRange": [
0,
274
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "liquidai",
"url": "https://x.com/liquidai",
"twitterUrl": "https://twitter.com/liquidai",
"id": "1635809139808141320",
"name": "Liquid AI",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": "Business",
"profilePicture": "https://pbs.twimg.com/profile_images/1702611993327251456/PUUuOA4W_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1635809139808141320/1766688037",
"description": "",
"location": "Cambridge, MA",
"followers": 44270,
"following": 61,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Wed Mar 15 01:04:36 +0000 2023",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 3603,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 254,
"statusesCount": 1579,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2115128329003303107"
],
"profile_bio": {
"description": "Build efficient general-purpose AI at every scale.",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "liquid.ai",
"expanded_url": "https://www.liquid.ai",
"indices": [
0,
23
],
"url": "https://t.co/KwQwvrNUYn"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null,
"protected": false
},
"extendedEntities": {
"media": [
{
"additional_media_info": {
"monetizable": false
},
"display_url": "pic.x.com/yKN3VfZlxI",
"expanded_url": "https://x.com/liquidai/status/2115128329003303107/video/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"id_str": "2115125357439557633",
"indices": [
275,
298
],
"media_key": "13_2115125357439557633",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAAR1ab05hmyABAAA=",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAAECgABHVpvTmGbIAEAAA==",
"media_key": "13_2115125357439557633"
}
},
"media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2115125357439557633/img/X_jB63rlX-TyinU4.jpg",
"original_info": {
"focus_rects": [],
"height": 2160,
"width": 3840
},
"sizes": {
"large": {
"h": 1152,
"w": 2048
}
},
"type": "video",
"url": "https://t.co/yKN3VfZlxI",
"video_info": {
"aspect_ratio": [
16,
9
],
"duration_millis": 137109,
"variants": [
{
"content_type": "application/x-mpegURL",
"url": "https://video-s.twimg.com/amplify_video/2115125357439557633/pl/KVzj8jpHnBdT-RID.m3u8?tag=29&v=ef5"
},
{
"bitrate": 256000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2115125357439557633/vid/avc1/480x270/a3jUU4r5ZJtMO95x.mp4?tag=29"
},
{
"bitrate": 832000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2115125357439557633/vid/avc1/640x360/cK-vOef5wu-gJq-9.mp4?tag=29"
},
{
"bitrate": 2176000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2115125357439557633/vid/avc1/1280x720/KeRXXul_iF29OCSy.mp4?tag=29"
},
{
"bitrate": 10368000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2115125357439557633/vid/avc1/1920x1080/aUo57T3ugLpDzRcp.mp4?tag=29"
},
{
"bitrate": 25128000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2115125357439557633/vid/avc1/3840x2160/MGX33ddyGxppZZvZ.mp4?tag=29"
}
]
}
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": []
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"isLimitedReply": false,
"communityInfo": null,
"article": null
}