LLM EU
Roghchlár

Mistral Small 4 (119B-A6B)

Mistral AI · Soláthraithe EU

Gan óstáil — inneall cúil mock Meáchain oscailte Soláthraí Eorpach

Ceannasacht agus óstáil

Gan óstáil — inneall cúil mock

Níl sé óstáilte ar LLM EU ar an imscaradh seo: freagraíonn an t-inneall cúil mock ionsuite i réigiún dev-mock na hiarratais. Ní ritheann aon mheáchain.

Achoimre

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.

Sonraíochtaí

Soláthraí
Mistral AI (FR)
Fuinneog chomhthéacs
262k
Paraiméadair
119.4B
Módúlachtaí
text, vision
Ceadúnas
apache-2.0 · licence
Meáchain oscailte
yes
Dáta scaoilte
23 Ean 2026
Tascanna
coding, reasoning, vision, multilingual-support, summarization

Teangacha

Láidir: en, fr, de, es, it, pt

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

Teangacha

Láidir

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

Leordhóthanach

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

Gan fíorú: níl an t-éileamh seo doiciméadaithe ag an soláthraí. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Cathain a úsáidfear é

Láidreachtaí

  • 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

Teorainneacha

  • 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