LLM EU
Meni
Modeli

NVIDIA Nemotron 3 Nano Omni 30B-A3B Reasoning

NVIDIA

Samo v katalogu Odprte uteži

Nazadnje pregledano:

Suverenost in gostovanje

Samo v katalogu

Ta model je v katalogu za referenco. Na LLM EU še ni gostovan in noben lastni endpoint ga tukaj ne streže. Zahteve zanj gredo neposredno k ponudniku, pod lastnimi pogoji tega ponudnika.

Povzetek

NVIDIA Nemotron 3 Nano Omni 30B-A3B Reasoning je NVIDIA objavila kot odprte uteži z 33B parametri pod licenco nvidia-open-model-agreement (po meri, označeno kot "drugo"). Sprejme zvok in vrne besedilo. Objavljena konfiguracija ne beleži kontekstnega okna, zato ga ta kartica ne vsebuje. Kontrolna točka je uglašena z navodili in vključuje predlogo za klepet. Kartica je samo za katalog: LLM EU ne poganja tega modela. Založnik na strani modela ne navaja jezikovne pokritosti.

Specifikacije

Ponudnik
NVIDIA (US)
Kontekstno okno
Ni preverjeno: ponudnik te trditve ni dokumentiral.
Parametri
33B
Modalnosti
text, vision, audio
Licenca
other · licence
Odprte uteži
yes
Datum izdaje
20. apr. 2026
Naloge
Razmišljanje, Vid, Večjezična podpora

Jeziki

Močno: —

Zadostno: —

Močno

    Zadostno

      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

      • open weights are published on Hugging Face and can be downloaded without a vendor agreement
      • instruction-tuned checkpoint with a chat template in the repository
      • speech recognition runs locally, so audio never leaves the operator premises

      Omejitve

      • catalogue only — LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
      • no evaluation has been run by LLM EU
      • the nvidia-open-model-agreement (other) licence is a custom agreement whose commercial terms were not established from its published text, so commercial serving is not permitted until a human clears it; the router must not route to it
      • the published configuration records no context window, so the card carries none
      • at 33B parameters, self-hosting needs a high-memory accelerator
      • vision checkpoints are heavier to serve than their parameter count alone suggests, because the image encoder and pre-processing run alongside the language model