LLM EU
Meni

Mistral Small 4 (119B-A6B)

Mistral AI · Ponudniki EU

Ni gostovano — mock zaledje Odprte uteži Evropski ponudnik

Suverenost in gostovanje

Ni gostovano — mock zaledje

V tej uvedbi ni gostovano na LLM EU: na zahteve odgovarja vgrajeno mock zaledje v območju dev-mock. Nobene uteži se ne izvajajo.

Povzetek

Mistral Small 4 is an Apache-2.0 mixture-of-experts model with 119B total parameters and 6.5B activated per token. It accepts text and images and generates text over a 256k-token context window. Mistral describes it as one model that covers instruct, reasoning and coding use, and ships an NVFP4 checkpoint for smaller servers.

Specifikacije

Ponudnik
Mistral AI (FR)
Kontekstno okno
262k
Parametri
119.4B
Modalnosti
text, vision
Licenca
apache-2.0 · licence
Odprte uteži
yes
Datum izdaje
23. jan. 2026
Naloge
coding, reasoning, vision, multilingual-support, summarization

Jeziki

Močno: en, fr, de, es, it, pt

Zadostno: nl, pl, ro, sv, cs, uk, ru, zh, ja, ko, ar, hi, tr, vi, id, fa

Jeziki

Močno

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

Zadostno

  • nl
  • pl
  • ro
  • sv
  • cs
  • uk
  • ru
  • zh
  • ja
  • ko
  • ar
  • hi
  • tr
  • vi
  • id
  • fa

Ni preverjeno: ponudnik te trditve ni dokumentiral. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Kdaj ga uporabiti

Prednosti

  • Apache-2.0 licence, so commercial serving is permitted
  • 256k-token context window
  • text and image input in one checkpoint
  • low activated parameter count per token
  • vendor-published NVFP4 and speculative-decoding checkpoints

Omejitve

  • Vendor latency and throughput comparisons against Mistral Small 3 are self-reported
  • weights are 119B parameters, so self-hosting needs a large-memory accelerator
  • no evaluation has been run by LLM EU