Primerjaj

DeepSeek R1 Distill Qwen 1.5B vs DeepSeek R1 0528

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.

DeepSeek R1 Distill Qwen 1.5BDeepSeek R1 0528
Ponudnik DeepSeekDeepSeek
Parametri 1.8B684.5B
Kontekstno okno Ni preverjeno: ponudnik te trditve ni dokumentiral.Ni preverjeno: ponudnik te trditve ni dokumentiral.
Licenca mitmit
Modalnosti texttext
Datum izdaje 20. jan. 202528. maj 2025
Jeziki Ni preverjeno: ponudnik te trditve ni dokumentiral.Ni preverjeno: ponudnik te trditve ni dokumentiral.
Odprte uteži dada
Naloge Razmišljanje, Nizki stroškiRazmišljanje, Kodiranje

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

DeepSeek R1 Distill Qwen 1.5B

Prednosti

  • open weights are published on Hugging Face and can be downloaded without a vendor agreement
  • mit licence, so commercial self-hosting is permitted without a separate agreement
  • at 1.8B parameters it fits on a single accelerator

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 published configuration records no context window, so the card carries none
  • at 1.8B parameters, the weights fit on a single modest accelerator

Naloge

Razmišljanje, Nizki stroški

DeepSeek R1 0528

Prednosti

  • open weights are published on Hugging Face and can be downloaded without a vendor agreement
  • mit licence, so commercial self-hosting is permitted without a separate agreement

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 published configuration records no context window, so the card carries none
  • at 684.5B parameters, self-hosting needs a multi-node deployment rather than a single server

Naloge

Razmišljanje, Kodiranje

Naloge: Razmišljanje

Primerjaj modele

Primerjaj modele →