{"article":{"annotation":{"article_id":"liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026","available_at":"2026-10-15T18:14:01.782491Z","geography_revision":"ef6ee0010dda5fe7b240fd514749b43e214c57da73222d2e40ec83b276dd0977","id":"fc00b9fb1b70fff584df95da592331955484418a21eaeb43b862ea2cdd042041","input_sha256":"f8fc10f1163fc03025a9c4076202ec405e25a6c01edf3f56a60879f60b514265","limitations":["Rule-derived subjects are candidates, not verified editorial labels or calibrated model probabilities.","Coverage is distinct from event location. Unknown country/city/coordinates remain absent; no automatic geocoding.","Article geometries keep their stated precision and methodology; reproducing them is not independent coordinate verification."],"method":"controlled-rules-v1","places":[{"admin1":null,"city":null,"coordinate_note":null,"coordinate_reference_system":"OGC:CRS84","coordinate_source":null,"country":"US","evidence":[{"field":"country","language":"en","note":"Explicit preserved editorial country/region; no city or national centroid inferred","source_urls":["https://www.liquid.ai/blog/lfm2-5-24b-a2b"]}],"geometry":null,"id":"iso3166-1:US","kind":"country-or-area","labels":{"ar":"الولايات المتحدة الأمريكية","en":"United States of America","es":"Estados Unidos de América","fr":"États-Unis d’Amérique"},"match_status":"candidate","precision":"regional","role":"coverage","uncertainty_m":null}],"rules_sha256":"fb5ad3c27c91cb840f7a0a05f7f64a5cb26ad0374409ff9457f277c7092e22b4","schema_version":1,"subjects":[{"concept_id":"medtop:20001298","confidence":null,"confidence_method":null,"evidence":[{"field":"en.title+en.summary","language":"en","note":"Subject suggested from the title or summary: AI","source_urls":["https://www.liquid.ai/blog/lfm2-5-24b-a2b"]}],"method":"controlled-rules-v1","rule_id":"artificial-intelligence","status":"candidate"}],"taxonomy_revision":"1f2db31d811fca07e99b16d402c10e2cc2965c9df1c7b41d9be348b40a24e7fb","taxonomy_version":"IPTC Media Topics 2026-Q2"},"api_url":"https://newsverum.com/api/v1/articles/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026?lang=fr","category":"technology","content":{"key_points":[],"paragraphs":["Liquid AI a publié le 13 octobre LFM2.5-24B-A2B, un modèle de raisonnement à poids ouverts destiné aux agents locaux. Ce modèle à mélange d’experts compte 24 milliards de paramètres au total et en active deux milliards par jeton. Par rapport à son prédécesseur, Liquid AI indique que la fenêtre de contexte passe de 32 768 à 131 072 jetons, le vocabulaire de 65 000 à 128 000 et le préentraînement de 17 à 33 billions de jetons.","L’entreprise rapporte 184 jetons générés par seconde sur Apple M5 Max et plus de 21 000 jetons de sortie par seconde sur un seul NVIDIA B300. Ce dernier chiffre provient d’une charge soutenue à forte concurrence et ne représente pas le débit d’un utilisateur unique; les deux mesures viennent du dispositif de test de Liquid AI. Son tableau montre des résultats mitigés : le modèle devance ou égale les concurrents dans cinq tests d’usage d’outils sur huit, mais reste derrière des modèles plus grands sur certains tests de connaissances et de programmation."],"sections":[]},"corrections":[],"country":"US","data":{"blocks":[{"description":{"ar":"تقول الشركة إن ملياري معلمة تنشطان لكل رمز، مع نتائج تختلف بحسب الجهاز.","de":"Laut Unternehmen sind je Token zwei Milliarden Parameter aktiv; die Werte hängen von der Hardware ab.","en":"The company says two billion parameters are active per token and reports device-specific results.","es":"La empresa dice que activa 2.000 millones por token y publica resultados por dispositivo.","fr":"Selon l’entreprise, deux milliards de paramètres sont actifs par jeton; les résultats dépendent du matériel.","pt":"Segundo a empresa, dois mil milhões ficam ativos por token; os resultados variam conforme o equipamento.","tr":"Şirkete göre token başına iki milyar parametre etkin; hız sonuçları donanıma göre değişiyor."},"id":"announcement-record","items":[{"date":"2026-10-13","description":{"ar":"تقول الشركة إن ملياري معلمة تنشطان لكل رمز، مع نتائج تختلف بحسب الجهاز.","de":"Laut Unternehmen sind je Token zwei Milliarden Parameter aktiv; die Werte hängen von der Hardware ab.","en":"The company says two billion parameters are active per token and reports device-specific results.","es":"La empresa dice que activa 2.000 millones por token y publica resultados por dispositivo.","fr":"Selon l’entreprise, deux milliards de paramètres sont actifs par jeton; les résultats dépendent du matériel.","pt":"Segundo a empresa, dois mil milhões ficam ativos por token; os resultados variam conforme o equipamento.","tr":"Şirkete göre token başına iki milyar parametre etkin; hız sonuçları donanıma göre değişiyor."},"label":{"ar":"Liquid AI تطلق نموذج LFM2.5 بعدد 24 مليار معلمة","de":"Liquid AI veröffentlicht das 24-Milliarden-Parameter-Modell LFM2.5","en":"Liquid AI releases 24-billion-parameter LFM2.5 model","es":"Liquid AI lanza el modelo LFM2.5 de 24.000 millones de parámetros","fr":"Liquid AI lance le modèle LFM2.5 de 24 milliards de paramètres","pt":"Liquid AI lança o modelo LFM2.5 com 24 mil milhões de parâmetros","tr":"Liquid AI, 24 milyar parametreli LFM2.5 modelini yayımladı"},"status":"occurred"}],"methodology":{"ar":"يلخص سجل الحدث إعلان المصدر ولا يضيف تحققاً مستقلاً أو تعميماً يتجاوز ما ورد فيه.","de":"Dieser Ereigniseintrag fasst die Quelle zusammen und ergänzt keine unabhängige Prüfung oder Verallgemeinerung.","en":"This event record summarizes the source announcement and adds no independent verification or generalization beyond it.","es":"Este registro resume el anuncio de la fuente sin añadir verificación independiente ni generalizaciones.","fr":"Cette fiche résume l’annonce de la source sans ajouter de vérification indépendante ni généralisation.","pt":"Este registo resume o anúncio da fonte sem acrescentar verificação independente ou generalização.","tr":"Bu olay kaydı kaynağın duyurusunu özetler; kaynakta belirtilmeyen bağımsız doğrulama veya genelleme eklemez."},"sourceUrls":["https://www.liquid.ai/blog/lfm2-5-24b-a2b"],"title":{"ar":"ملخص الإعلان","de":"Zusammenfassung der Ankündigung","en":"Announcement summary","es":"Resumen del anuncio","fr":"Résumé de l’annonce","pt":"Resumo do anúncio","tr":"Duyuru özeti"},"type":"events","updatedAt":"2026-10-15T18:03:17Z"}],"version":1},"data_downloads":[{"formats":{"csv":"https://newsverum.com/api/v1/articles/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026/data/announcement-record?lang=fr&format=csv","json":"https://newsverum.com/api/v1/articles/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026/data/announcement-record?lang=fr&format=json"},"id":"announcement-record"}],"data_types":["events"],"editorial_illustration":{"alt":"Illustration conceptuelle de la technologie, des processeurs et des informations connectées.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"fr","scope":"topic","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"event_id":"event-3a3cc495-3284-535b-9397-6d57c35d94f4","event_period":"2026-10-13","event_period_basis":"event-or-reference-period","id":"liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026","image":null,"importance":0.6,"language":"fr","modified_at":"2026-10-15T18:13:44+00:00","publication_basis":"publication-record","published_at":"2026-10-15T18:13:44+00:00","reading_minutes":1,"region":"world","section_illustration":{"alt":"Illustration conceptuelle de la technologie, des processeurs et des informations connectées.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"fr","scope":"section","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"slug":"liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026","sources":[{"checkedAt":"2026-10-15","name":"Liquid AI","publishedAt":"2026-10-13","url":"https://www.liquid.ai/blog/lfm2-5-24b-a2b"}],"summary":"Selon l’entreprise, deux milliards de paramètres sont actifs par jeton; les résultats dépendent du matériel.","text":"Selon l’entreprise, deux milliards de paramètres sont actifs par jeton; les résultats dépendent du matériel.\n\nLiquid AI a publié le 13 octobre LFM2.5-24B-A2B, un modèle de raisonnement à poids ouverts destiné aux agents locaux. Ce modèle à mélange d’experts compte 24 milliards de paramètres au total et en active deux milliards par jeton. Par rapport à son prédécesseur, Liquid AI indique que la fenêtre de contexte passe de 32 768 à 131 072 jetons, le vocabulaire de 65 000 à 128 000 et le préentraînement de 17 à 33 billions de jetons.\n\nL’entreprise rapporte 184 jetons générés par seconde sur Apple M5 Max et plus de 21 000 jetons de sortie par seconde sur un seul NVIDIA B300. Ce dernier chiffre provient d’une charge soutenue à forte concurrence et ne représente pas le débit d’un utilisateur unique; les deux mesures viennent du dispositif de test de Liquid AI. Son tableau montre des résultats mitigés : le modèle devance ou égale les concurrents dans cinq tests d’usage d’outils sur huit, mais reste derrière des modèles plus grands sur certains tests de connaissances et de programmation.","title":"Liquid AI lance le modèle LFM2.5 de 24 milliards de paramètres","topics":[],"translations":[{"api_url":"https://newsverum.com/api/v1/articles/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026?lang=tr","language":"tr","url":"https://newsverum.com/tr/news/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026"},{"api_url":"https://newsverum.com/api/v1/articles/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026?lang=en","language":"en","url":"https://newsverum.com/en/news/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026"},{"api_url":"https://newsverum.com/api/v1/articles/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026?lang=ar","language":"ar","url":"https://newsverum.com/ar/news/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026"},{"api_url":"https://newsverum.com/api/v1/articles/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026?lang=fr","language":"fr","url":"https://newsverum.com/fr/news/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026"},{"api_url":"https://newsverum.com/api/v1/articles/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026?lang=es","language":"es","url":"https://newsverum.com/es/news/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026"},{"api_url":"https://newsverum.com/api/v1/articles/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026?lang=de","language":"de","url":"https://newsverum.com/de/news/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026"},{"api_url":"https://newsverum.com/api/v1/articles/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026?lang=pt","language":"pt","url":"https://newsverum.com/pt/news/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026"}],"url":"https://newsverum.com/fr/news/liquid-ai-releases-lfm25-24b-a2b-on-device-model-2026"},"version":"1"}