Primerjaj
DeepSeek R1 Distill Qwen 7B vs DeepSeek-R1-Distill-Qwen-32B
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 7B | DeepSeek-R1-Distill-Qwen-32B | |
|---|---|---|
| Ponudnik | DeepSeek | DeepSeek |
| Parametri | 7.6B | 32.76B |
| Kontekstno okno | Ni preverjeno: ponudnik te trditve ni dokumentiral. | 131k |
| Licenca | mit | mit |
| Modalnosti | text | text |
| Datum izdaje | 20. jan. 2025 | 20. jan. 2025 |
| Jeziki | Ni preverjeno: ponudnik te trditve ni dokumentiral. | Močno: en, zh Zadostno: de, fr, es, it, pt, ru |
| Odprte uteži | da | da |
| Naloge | Razmišljanje, Nizki stroški | Razmišljanje, Kodiranje, Nizki stroški, 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
DeepSeek R1 Distill Qwen 7B
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 7.6B 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 7.6B parameters, the weights fit on a single modest accelerator
Naloge
DeepSeek-R1-Distill-Qwen-32B
Prednosti
- fits a single 80GB accelerator
- MIT licence
- retains the R1 reasoning style that smaller base models usually lack
Omejitve
- a distillation, so quality is bounded by the teacher
- long reasoning traces increase output cost
- no evaluation has been run by LLM EU
Naloge
Naloge: Razmišljanje, Nizki stroški
Primerjaj modele
Primerjaj modele →- Command R (08-2024) vs DeepSeek-R1-Distill-Qwen-32B
- Deepseek Coder 7B Instruct V1.5 vs DeepSeek R1 Distill Qwen 7B
- DeepSeek R1 Distill Qwen 1.5B vs DeepSeek R1 Distill Qwen 7B
- DeepSeek-R1-Distill-Qwen-32B vs Devstral Small 2 (24B)
- DeepSeek-R1-Distill-Qwen-32B vs ERNIE 4.5 21B-A3B Thinking
- DeepSeek-R1-Distill-Qwen-32B vs ERNIE 4.5 VL 28B-A3B