LLM EU
Menüü

Llama 4 Scout 17B-16E Instruct

Meta

Ainult kataloogis Avatud kaalud

Suveräänsus ja majutamine

Ainult kataloogis

See mudel on loetletud viitamiseks. Seda ei majutata veel LLM EU-s ega teeninda seda siin ükski esimese osapoole lõpp-punkt. Päringud suunatakse otse pakkujale, pakkuja enda tingimustel.

Kokkuvõte

Llama 4 Scout is a natively multimodal mixture-of-experts model with 17B active parameters, 16 experts and 109B total parameters. Meta advertises a 10 million token context window for it, the largest of any Llama release, and states it fits on a single H100 with Int4 quantisation. It is released under the Llama 4 Community License, which keeps the 700M monthly-active-user threshold.

Tehnilised andmed

Pakkuja
Meta (US)
Konteksti aken
10.5M
Parameetrid
108.64B
Modaalsused
text, vision
Litsents
other · licence
Avatud kaalud
yes
Avaldamiskuupäev
05. apr 2025
Ülesanded
vision, summarization, rag, multilingual-support

Keeled

Tugev: en, de, fr, es, it, pt, hi

Piisav: ar, id, th, tl, vi

Keeled

Tugev

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

Piisav

  • ar
  • id
  • th
  • tl
  • vi

Verifitseerimata: pakkuja ei ole seda väidet dokumenteerinud. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Millal kasutada

Tugevused

  • 10M-token context window, the longest published in the Llama line
  • multimodal input with image grounding
  • fits a single H100 at Int4 quantisation

Piirangud

  • Llama 4 Community License, not an OSI licence
  • 109B total parameters make full-precision serving expensive
  • long-context quality at the 10M limit is not independently verified