Mistral Small 4 (119B-A6B)

Mistral AI · Proveedores EU

No alojado — backend mock Pesos abiertos Proveedor europeo

Soberanía y alojamiento

No alojado — backend mock

No alojado en LLM EU en este despliegue: las solicitudes las responde el backend mock integrado en la región dev-mock. No se ejecuta ningún peso.

Resumen

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.

Especificaciones

Proveedor
Mistral AI (FR)
Ventana de contexto
262k
Parámetros
119.4B
Modalidades
text, vision
Licencia
apache-2.0 · licence
Pesos abiertos
yes
Fecha de lanzamiento
23 ene 2026
Tareas
coding, reasoning, vision, multilingual-support, summarization

Idiomas

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

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

Idiomas

Fuerte

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

Adecuado

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

No verificado: el proveedor no ha documentado esta afirmación. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Cuándo usarlo

Puntos fuertes

  • 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

Límites

  • 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