Compare
DeepSeek R1 Distill Qwen 1.5B vs DeepSeek-R1-Distill-Qwen-32B
Put two to four models side by side on the fields that decide a deployment: context, price, region, license, languages, hosting, and what is verified.
| DeepSeek R1 Distill Qwen 1.5B | DeepSeek-R1-Distill-Qwen-32B | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Parameters | 1.8B | 32.76B |
| Context window | Not verified: the provider has not documented this claim. | 131k |
| License | mit | mit |
| Modalities | text | text |
| Release date | 20 Jan 2025 | 20 Jan 2025 |
| Languages | Not verified: the provider has not documented this claim. | Strong: en, zh Adequate: de, fr, es, it, pt, ru |
| Open weights | yes | yes |
| Tasks | Reasoning, Low cost | Reasoning, Coding, Low cost, Summarisation |
Where two models differ, this table shows the difference and stops. LLM EU publishes no winner badge without a documented score for that task, and a missing figure stays missing instead of becoming a zero.
When to use it
DeepSeek R1 Distill Qwen 1.5B
Strengths
- 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
Limits
- 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
Tasks
DeepSeek-R1-Distill-Qwen-32B
Strengths
- fits a single 80GB accelerator
- MIT licence
- retains the R1 reasoning style that smaller base models usually lack
Limits
- a distillation, so quality is bounded by the teacher
- long reasoning traces increase output cost
- no evaluation has been run by LLM EU