Devstral Small 2 (24B)

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

Devstral Small 2 is a 24B Apache-2.0 model fine-tuned for software-engineering agents, built with All Hands AI. The model card reports 68.0% on SWE-bench Verified and 55.7% on SWE-bench Multilingual. It is text-only: the vision encoder of its Mistral Small base was removed during fine-tuning.

Speċifikazzjonijiet

Fornitur
Mistral AI (FR)
Tieqa tal-kuntest
262k
Parametri
24.01B
Modalitajiet
text, code
Liċenza
apache-2.0 · licence
Piżijiet miftuħa
yes
Data tal-ħruġ
28 Nov 2025
Kompiti
coding, rag, reasoning

Lingwi

Qawwi: en

Adekwat: fr, de, es, it, pt, zh, ja, ko

Lingwi

Qawwi

  • en

Adekwat

  • fr
  • de
  • es
  • it
  • pt
  • zh
  • ja
  • ko

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

  • agentic coding: multi-file edits and tool use in repositories
  • long 256k-token context window for large codebases
  • Apache-2.0 licence permits commercial self-hosting
  • vendor-published SWE-bench Multilingual score

Limiti

  • text-only, no image input
  • benchmark scores are self-reported by the vendor
  • no evaluation has been run by LLM EU