Mistral Large 3 (675B)

Mistral AI · Pružatelji EU

Samo katalog Otvoreni utezi Europski pružatelj

Suverenost i hosting

Samo katalog

Ovaj je model u katalogu za referencu. Još nije hostan na LLM EU i nijedna vlastita krajnja točka ga ovdje ne poslužuje. Zahtjevi za njega idu izravno pružatelju, prema uvjetima tog pružatelja.

Sažetak

Mistral Large 3 is the largest published Mistral model: a granular mixture-of-experts model with 675B total parameters and 41B active parameters, released under Apache-2.0. It is multimodal and supports a 256k-token context window. The vendor states it was trained from scratch on 3000 H200 GPUs.

Specifikacije

Pružatelj
Mistral AI (FR)
Kontekstni prozor
262k
Parametri
675B
Modaliteti
text, vision
Licenca
apache-2.0 · licence
Otvoreni utezi
yes
Datum izlaska
28. stu 2025.
Zadaci
reasoning, coding, multilingual-support, vision, summarization

Jezici

Jako: en, fr, es, de, it, pt

Zadovoljavajuće: nl, zh, ja, ko, ar

Jezici

Jako

  • en
  • fr
  • es
  • de
  • it
  • pt

Zadovoljavajuće

  • nl
  • zh
  • ja
  • ko
  • ar

Nije provjereno: pružatelj nije dokumentirao ovu tvrdnju. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Kada ga koristiti

Prednosti

  • frontier-scale open weights under a permissive licence
  • 41B active parameters keep decoding cheaper than the total size suggests
  • 256k-token context window
  • vendor-published NVFP4 checkpoint for single-node deployment

Ograničenja

  • 675B parameters require multi-GPU nodes even quantised to NVFP4
  • no independent evaluation has been run by LLM EU
  • vendor benchmark comparisons are self-reported