Mistral Small 4 (119B-A6B)
Mistral AI · Aanbieders EU
Soevereiniteit en hosting
Niet gehost op LLM EU in deze deployment: verzoeken worden beantwoord door de ingebouwde mockbackend in regio dev-mock. Er worden geen gewichten uitgevoerd.
Samenvatting
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.
Specificaties
- Aanbieder
- Mistral AI (FR)
- Contextvenster
- 262k
- Parameters
- 119.4B
- Modaliteiten
- text, vision
- Licentie
- apache-2.0 · licence
- Open gewichten
- yes
- Releasedatum
- 23 jan 2026
- Taken
- coding, reasoning, vision, multilingual-support, summarization
Talen
Sterk: en, fr, de, es, it, pt
Voldoende: nl, pl, ro, sv, cs, uk, ru, zh, ja, ko, ar, hi, tr, vi, id, fa
Talen
Sterk
- en
- fr
- de
- es
- it
- pt
Voldoende
- nl
- pl
- ro
- sv
- cs
- uk
- ru
- zh
- ja
- ko
- ar
- hi
- tr
- vi
- id
- fa
Niet geverifieerd: de aanbieder heeft deze claim niet gedocumenteerd. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.
Wanneer te gebruiken
Sterke punten
- 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
Beperkingen
- 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