gpt-oss-120b
Suverenost in gostovanje
Ta model je v katalogu za referenco. Na LLM EU še ni gostovan in nobena lastna končna točka ga tukaj ne streže. Zahteve zanj gredo neposredno k ponudniku, pod lastnimi pogoji tega ponudnika.
Povzetek
gpt-oss-120b is OpenAI’s open-weight reasoning model, a mixture-of-experts model with 117B total and 5.1B activated parameters under the Apache-2.0 licence. It runs on a single 80GB GPU because the expert weights are post-trained in MXFP4, and the configuration declares a context window of 131,072 tokens. It must be used with OpenAI’s harmony response format and exposes three reasoning-effort levels.
Specifikacije
- Ponudnik
- OpenAI (US)
- Kontekstno okno
- 131k
- Parametri
- 116.83B
- Modalnosti
- text
- Licenca
- apache-2.0 · licence
- Odprte uteži
- yes
- Datum izdaje
- 05. avg. 2025
- Naloge
- reasoning, coding, rag, summarization
Jeziki
Močno: en
Zadostno: de, fr, es, it, pt, ja, ko, zh, ar
Jeziki
Močno
- en
Zadostno
- de
- fr
- es
- it
- pt
- ja
- ko
- zh
- ar
Ni preverjeno: ponudnik te trditve ni dokumentiral. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.
Kdaj ga uporabiti
Prednosti
- Apache-2.0 licence with no user threshold
- runs on a single 80GB accelerator
- configurable reasoning effort with full chain-of-thought access
- native function calling, browsing and structured output
Omejitve
- requires the harmony response format; other prompt templates degrade it
- 117B parameters must be resident even though only 5.1B are active
- chain-of-thought output is not intended for end users