LLM EU
Meni
Primerjaj

NVIDIA Nemotron 3 Nano Omni 30B-A3B Reasoning vs NVIDIA Nemotron 3 Super 120B-A12B

Postavite dva do štiri modele enega ob drugega glede na polja, ki odločajo o uvedbi: kontekst, cena, regija, licenca, jeziki, gostovanje in kaj je preverjeno.

NVIDIA Nemotron 3 Nano Omni 30B-A3B ReasoningNVIDIA Nemotron 3 Super 120B-A12B
Ponudnik NVIDIANVIDIA
Parametri 33B123.61B
Kontekstno okno Ni preverjeno: ponudnik te trditve ni dokumentiral.262k
Licenca otherother
Modalnosti text, vision, audiotext
Datum izdaje 20. apr. 202610. mar. 2026
Jeziki Ni preverjeno: ponudnik te trditve ni dokumentiral.Močno: en, fr, es, it, de
Zadostno: ja, zh
Odprte uteži dada
Naloge Razmišljanje, Vid, Večjezična podporaRazmišljanje, Kodiranje, Pridobivanje (RAG), Povzemanje

Kjer se dva modela razlikujeta, ta tabela pokaže razliko in se ustavi. LLM EU ne objavi značke zmagovalca brez dokumentirane ocene za to nalogo, manjkajoča številka pa ostane manjkajoča, namesto da bi postala nič.

Kdaj ga uporabiti

NVIDIA Nemotron 3 Nano Omni 30B-A3B Reasoning

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

Naloge

Razmišljanje, Vid, Večjezična podpora

NVIDIA Nemotron 3 Super 120B-A12B

Prednosti

  • strong published long-context scores up to 1M tokens
  • 12B active parameters keep inference cost below the total size
  • inference and agentic benchmark tables published with harness links
  • source-available vendor licence with published evaluation tooling

Omejitve

  • NVIDIA Nemotron Open Model License, a vendor licence rather than an OSI one
  • seven declared languages, fewer than the European-focused models
  • long-context scores come from NVIDIA’s own harness

Naloge

Razmišljanje, Kodiranje, Pridobivanje (RAG), Povzemanje

Naloge: Razmišljanje

Primerjaj modele

Primerjaj modele →