Title: DeepSeek R1 Distill Qwen 1.5B vs DeepSeek-R1-Distill %E2%80%94 LLM EU
Canonical: https://llmeu.com/mt/compare/deepseek-r1-distill-qwen-1-5b-vs-deepseek-r1-distill-qwen-32b/
Markdown mirror: https://llmeu.com/mt/compare/deepseek-r1-distill-qwen-1-5b-vs-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

# DeepSeek R1 Distill Qwen 1.5B vs DeepSeek-R1-Distill-Qwen-32B

Qieg%C4%A7ed %C5%BCew%C4%A1 mudelli sa erbg%C4%A7a ma' xulxin fuq l-oqsma li jidde%C4%8Biedu deployment: kuntest, prezz, re%C4%A1jun, li%C4%8Benzja, lingwi, hosting, u x'hu verifikat.

Fejn %C5%BCew%C4%A1 mudelli jvarjaw, din it-tabella turi d-differenza u tieqaf. LLM EU ma tippubblikax badge ta' rebbie%C4%A7 ming%C4%A7ajr punte%C4%A1%C4%A1 dokumentat g%C4%A7al dik il-kompitu, u figura nieqsa tibqa' nieqsa minflok ma ssir %C5%BCero.

## Meta tu%C5%BCah

### [DeepSeek R1 Distill Qwen 1.5B](/mt/models/deepseek-r1-distill-qwen-1-5b/)

#### Sa%C4%A7%C4%A7iet

- 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

#### Limiti

- catalogue only %E2%80%94 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

#### Kompiti

[Ra%C4%A1unament](/mt/tasks/reasoning/), [Spi%C5%BCa baxxa](/mt/tasks/cheap/)

### [DeepSeek-R1-Distill-Qwen-32B](/mt/models/deepseek-r1-distill-qwen-32b/)

#### Sa%C4%A7%C4%A7iet

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

#### Limiti

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

#### Kompiti

[Ra%C4%A1unament](/mt/tasks/reasoning/), [Ikkodifikar](/mt/tasks/coding/), [Spi%C5%BCa baxxa](/mt/tasks/cheap/), [Sommarizzazzjoni](/mt/tasks/summarization/)

**Kompiti:** [Ra%C4%A1unament](/mt/tasks/reasoning/), [Spi%C5%BCa baxxa](/mt/tasks/cheap/)

## Qabbel mudelli

- [Bloom 1b1 vs DeepSeek R1 Distill Qwen 1.5B](/mt/compare/bloom-1b1-vs-deepseek-r1-distill-qwen-1-5b/)
- [Command R (08-2024) vs DeepSeek-R1-Distill-Qwen-32B](/mt/compare/command-r-08-2024-vs-deepseek-r1-distill-qwen-32b/)
- [NVIDIA Cosmos Reason2 2B vs DeepSeek R1 Distill Qwen 1.5B](/mt/compare/cosmos-reason2-2b-vs-deepseek-r1-distill-qwen-1-5b/)
- [DeepSeek OCR vs DeepSeek R1 Distill Qwen 1.5B](/mt/compare/deepseek-ocr-vs-deepseek-r1-distill-qwen-1-5b/)
- [DeepSeek R1 Distill Qwen 1.5B vs DeepSeek-R1](/mt/compare/deepseek-r1-distill-qwen-1-5b-vs-deepseek-r1/)
- [DeepSeek R1 Distill Qwen 1.5B vs DeepSeek R1 0528](/mt/compare/deepseek-r1-distill-qwen-1-5b-vs-deepseek-r1-0528/)