gpt-oss-20b

OpenAI

Katalgu biss Piżijiet miftuħa

Sovranità u hosting

Katalgu biss

Dan il-mudell huwa katalogat għal referenza. Mhuwiex ospitat fuq LLM EU bħalissa, u l-ebda endpoint tal-ewwel parti ma jservih hawn. Talbiet lejh imorru direttament għand il-fornitur, taħt it-termini tal-fornitur stess.

Sommarju

gpt-oss-20b is the smaller of OpenAI’s two open-weight reasoning models: 21B total parameters, 3.6B active, Apache-2.0 licensed and small enough to run in about 16GB of memory. Its configuration declares the same 131,072-token context window as the 120B model. It targets local and latency-sensitive deployments rather than peak quality.

Speċifikazzjonijiet

Fornitur
OpenAI (US)
Tieqa tal-kuntest
131k
Parametri
20.91B
Modalitajiet
text
Liċenza
apache-2.0 · licence
Piżijiet miftuħa
yes
Data tal-ħruġ
05 Aww 2025
Kompiti
reasoning, cheap, coding, rag

Lingwi

Qawwi: en

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

Lingwi

Qawwi

  • en

Adekwat

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

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

  • runs in about 16GB of memory
  • same 131,072-token window as the larger sibling
  • Apache-2.0 licence
  • reasoning-effort control

Limiti

  • quality clearly below the 120B model
  • harmony response format required
  • no evaluation has been run by LLM EU