LLM EU
Menu
Mudelli

gpt-oss-20b

OpenAI

Katalgu biss Piżijiet miftuħa

Aħħar reviżjoni:

Sovranità u ospitar

Katalgu biss

Dan il-mudell huwa kkatalgat għal referenza. Għadu mhux ospitat fuq LLM EU, u l-ebda endpoint tal-ewwel parti ma jservih hawn. It-talbiet lejh imorru direttament għand il-fornitur, taħt it-termini tal-fornitur stess.

Sommarju

gpt-oss-20b huwa l-iżgħar miż-żewġ mudelli ta' raġunament b'piż miftuħ ta' OpenAI: 21B parametru totali, 3.6B attivi, liċenzjat Apache-2.0 u żgħir biżżejjed biex jaħdem f'madwar 16GB ta' memorja. Il-konfigurazzjoni tiegħu tiddikjara l-istess tieqa ta' kuntest ta' 131,072 token bħall-mudell 120B. Jimmira skjeramenti lokali u sensittivi għal latenza aktar milli kwalità massima.

Speċifikazzjonijiet

Fornitur
OpenAI (US)
Tieqa tal-kuntest
131k
Parametri
20.91B
Modalitajiet
text
Liċenzja
apache-2.0 · licence
Piżijiet miftuħa
yes
Data tar-rilaxx
05 Aww 2025
Kompiti
Raġunament, Spiża baxxa, Ikkodifikar, Irkupru (RAG)

Lingwi

Qawwi: en

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

Qawwi

  • en

Adekwat

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

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

Meta tużah

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

Mistoqsijiet frequenti

Is gpt-oss-20b served on LLM EU?

It has no endpoint in the catalogue, so it is catalogue only — not hosted on LLM EU yet, with no region and no retention to report. A card whose status is "listed" is a catalogue entry, not a running deployment.

Under what licence is gpt-oss-20b released?

gpt-oss-20b is recorded under apache-2.0. The recorded licence text is https://www.apache.org/licenses/LICENSE-2.0. The weights are downloadable (open_weights is true). LLM EU republishes the licence id and the link and gives no legal advice; the licence text governs.

How large is gpt-oss-20b, and what context window does it have?

gpt-oss-20b is recorded at 21B total, 3.6B active (safetensors total 20,914,757,184) (source: https://huggingface.co/openai/gpt-oss-20b), with a context window of 131072 tokens (source: https://huggingface.co/openai/gpt-oss-20b/blob/main/config.json).