Title: DeepSeek-R1-Distill-Qwen-32B | LLM EU
Canonical: https://llmeu.com/hu/models/deepseek-r1-distill-qwen-32b/
Markdown mirror: https://llmeu.com/hu/models/deepseek-r1-distill-qwen-32b.md
Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json
Provider: DeepSeek
Licence: mit
Hosting: catalogue only %E2%80%94 not hosted on LLM EU yet
Sources: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

# DeepSeek-R1-Distill-Qwen-32B

[DeepSeek](/hu/providers/deepseek/)

Utols%C3%B3 ellen%C5%91rz%C3%A9s: 2026. okt. 14.

## Szuverenit%C3%A1s %C3%A9s hosting

Ez a modell referenciak%C3%A9nt szerepel a katal%C3%B3gusban. Az LLM EU m%C3%A9g nem %C3%BCzemelteti, %C3%A9s itt saj%C3%A1t v%C3%A9gpont nem szolg%C3%A1lja ki. A hozz%C3%A1 int%C3%A9zett k%C3%A9r%C3%A9sek k%C3%B6zvetlen%C3%BCl a szolg%C3%A1ltat%C3%B3hoz mennek, a szolg%C3%A1ltat%C3%B3 saj%C3%A1t felt%C3%A9telei szerint.

## %C3%96sszefoglal%C3%B3

A DeepSeek-R1-Distill-Qwen-32B egy 32 milli%C3%A1rdos s%C5%B1r%C5%B1 modell, amelyet a DeepSeek-R1-b%C5%91l desztill%C3%A1ltak egy Qwen2.5 alapra, MIT licenc alatt jelent meg. Megtartja az R1 %C3%A9rvel%C3%A9si viselked%C3%A9s%C3%A9t olyan m%C3%A9retben, amely elf%C3%A9r egy 80 GB-os gyors%C3%ADt%C3%B3n, konfigur%C3%A1ci%C3%B3s maximuma 131 072 token. A DeepSeek desztill%C3%A1ci%C3%B3k%C3%A9nt dokument%C3%A1lja, %C3%ADgy a plafonja a tan%C3%ADt%C3%B3 modell %C3%A9rvel%C3%A9se, nem pedig %C3%BAj k%C3%A9pz%C3%A9si futtat%C3%A1s.

## Specifik%C3%A1ci%C3%B3k

- Szolg%C3%A1ltat%C3%B3
  DeepSeek (CN)
- Kontextusablak
  131k
- Param%C3%A9terek
  32.76B
- Modalit%C3%A1sok
  text
- Licenc
  mit %C2%B7 [licence](https://opensource.org/license/mit)
- Ny%C3%ADlt s%C3%BAlyok
  yes
- Kiad%C3%A1s d%C3%A1tuma
  2025. jan. 20.
- Feladatok
  [%C3%89rvel%C3%A9s](/hu/tasks/reasoning/), [K%C3%B3dol%C3%A1s](/hu/tasks/coding/), [Alacsony k%C3%B6lts%C3%A9g](/hu/tasks/cheap/), [%C3%96sszefoglal%C3%A1s](/hu/tasks/summarization/)

## Nyelvek

**Er%C5%91s:** en, zh

**Megfelel%C5%91:** de, fr, es, it, pt, ru

#### Er%C5%91s

- en
- zh

#### Megfelel%C5%91

- de
- fr
- es
- it
- pt
- ru

Nincs ellen%C5%91rizve: a szolg%C3%A1ltat%C3%B3 nem dokument%C3%A1lta ezt az %C3%A1ll%C3%ADt%C3%A1st. %E2%80%94 a language is listed as strong only where a source claims it; the card links the evidence where one exists.

## Mikor %C3%A9rdemes haszn%C3%A1lni

#### Er%C5%91ss%C3%A9gek

- fits a single 80GB accelerator
- MIT licence
- retains the R1 reasoning style that smaller base models usually lack

#### Korl%C3%A1tok

- a distillation, so quality is bounded by the teacher
- long reasoning traces increase output cost
- no evaluation has been run by LLM EU

## Gyakran ism%C3%A9telt k%C3%A9rd%C3%A9sek

### Is DeepSeek-R1-Distill-Qwen-32B served on LLM EU?

It has no endpoint in the catalogue, so it is catalogue only %E2%80%94 not hosted on LLM EU yet, with no region and no retention to report. A card whose status is "listed" is a catalogue entry, not a running deployment.

### Under what licence is DeepSeek-R1-Distill-Qwen-32B released?

DeepSeek-R1-Distill-Qwen-32B is recorded under mit. The recorded licence text is https://opensource.org/license/mit. The weights are downloadable (open_weights is true). LLM EU republishes the licence id and the link and gives no legal advice; the licence text governs.

### How large is DeepSeek-R1-Distill-Qwen-32B, and what context window does it have?

DeepSeek-R1-Distill-Qwen-32B is recorded at 32.76B (safetensors total 32,763,876,352) (source: https://huggingface.co/api/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B), with a context window of 131072 tokens (source: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/config.json).

### %C3%81raz%C3%A1s

Ez a modell referenciak%C3%A9nt szerepel a katal%C3%B3gusban. Az LLM EU m%C3%A9g nem %C3%BCzemelteti, %C3%A9s itt saj%C3%A1t v%C3%A9gpont nem szolg%C3%A1lja ki. A hozz%C3%A1 int%C3%A9zett k%C3%A9r%C3%A9sek k%C3%B6zvetlen%C3%BCl a szolg%C3%A1ltat%C3%B3hoz mennek, a szolg%C3%A1ltat%C3%B3 saj%C3%A1t felt%C3%A9telei szerint.

### Ellen%C5%91rz%C3%A9si %C3%A1llapot

Ahol egy mez%C5%91nek nincs forr%C3%A1sa, a k%C3%A1rtya ellen%C5%91rizetlenk%C3%A9nt jelen%C3%ADti meg ahelyett, hogy kit%C3%B6lten%C3%A9. Az %C3%BCres mez%C5%91 is inform%C3%A1ci%C3%B3.

Az LLM EU Verified dokument%C3%A1lts%C3%A1got jelent, nem jogi tan%C3%BAs%C3%ADt%C3%A1st. Ez nem az AI Act szerinti megfelel%C5%91s%C3%A9g%C3%A9rt%C3%A9kel%C3%A9s, %C3%A9s az LLM EU nem EU-s szerv.

### Verzi%C3%B3k %C3%A9s v%C3%A1ltozatok

- catalogue %C2%B7 Csak katal%C3%B3gusban %C2%B7 [weights](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B)

### P%C3%A9ldak%C3%A9r%C3%A9s

```
curl https://api.llmeu.com/v1/chat/completions \
  -H "Authorization: Bearer $LLMEU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-r1-distill-qwen-32b","messages":[{"role":"user","content":"Hello"}]}'
```

Ehhez a modellhez nincs playground telep%C3%ADtve: egyetlen v%C3%A9gpont sem szolg%C3%A1lja ki, %C3%ADgy a k%C3%A9r%C3%A9snek nem lenne hov%C3%A1 mennie.

### Benchmarkok

Nincs k%C3%B6zz%C3%A9tett %C3%A9rt%C3%A9kel%C3%A9s. Ez hi%C3%A1ny, nem elrejtett eredm%C3%A9ny.

### Forr%C3%A1sok

- [huggingface.co](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B)

### A k%C3%A1rtya v%C3%A1ltoz%C3%A1snapl%C3%B3ja

- 2025. jan. 20. %E2%80%94 Kiad%C3%A1s d%C3%A1tuma
- 2026. okt. 14. %E2%80%94 Utols%C3%B3 ellen%C5%91rz%C3%A9s

Utols%C3%B3 ellen%C5%91rz%C3%A9s: 2026. okt. 14.