LLM EU
Izbornik

Mistral Small 4 (119B-A6B)

Mistral AI · Pružatelji EU

Nije hostano — mock backend Otvoreni utezi Europski pružatelj

Suverenost i hosting

Nije hostano — mock backend

Nije hostano na LLM EU u ovom postavljanju: na zahtjeve odgovara ugrađeni mock backend u regiji dev-mock. Ne izvršavaju se nikakve težine.

Sažetak

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

Pružatelj
Mistral AI (FR)
Kontekstni prozor
262k
Parametri
119.4B
Modaliteti
text, vision
Licenca
apache-2.0 · licence
Otvoreni utezi
yes
Datum izlaska
23. sij 2026.
Zadaci
coding, reasoning, vision, multilingual-support, summarization

Jezici

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

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

Jezici

Jako

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

Zadovoljavajuće

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

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

  • 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

Ograničenja

  • 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