Mistral Small 4 (119B-A6B)

Mistral AI · Fornituri EU

Mhux ospitat — backend mock Piżijiet miftuħa Fornitur Ewropew

Sovranità u hosting

Mhux ospitat — backend mock

Mhux ospitat fuq LLM EU fuq dan id-deployment: it-talbiet jiġu mwieġba mill-backend mock integrat fir-reġjun dev-mock. L-ebda weights m'jaħdmu.

Sommarju

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.

Speċifikazzjonijiet

Fornitur
Mistral AI (FR)
Tieqa tal-kuntest
262k
Parametri
119.4B
Modalitajiet
text, vision
Liċenza
apache-2.0 · licence
Piżijiet miftuħa
yes
Data tal-ħruġ
23 Jan 2026
Kompiti
coding, reasoning, vision, multilingual-support, summarization

Lingwi

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

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

Lingwi

Qawwi

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

Adekwat

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

Mhux verifikat: il-fornitur ma dokumentax din id-dikjarazzjoni. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Meta tużaha

Saħħiet

  • 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

Limiti

  • 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