DeepSeek-R1-Distill-32B is a distilled model built upon Qwen2.5-32B, incorporating the best reasoning algorithms from DeepSeek-R1 and expert knowledge. It sets new records among open-source dense models across several reasoning benchmarks: AIME 2024–72.6%, MATH-500–94.3%, and others. In practice, this model is nearly on par with the distilled 70-billion-parameter version and even surpasses it in certain tests.
Technically, the model is designed for solving expert-level tasks: complex mathematical computations, code generation and analysis, scientific research, and processing long or intricate contexts. DeepSeek-R1-Distill-32B can be integrated into enterprise systems, cloud services, and platforms for automating intellectual labor. For end-user applications, it is indispensable for building expert systems, scientific assistants, platforms for automating complex business processes, and educational solutions that require thorough and well-articulated explanations in responses.
DeepSeek-R1-Distill-32B is the choice for those seeking maximum performance among open-source models without the need to move to the heaviest systems.
| Model Name | Context | Type | GPU | Status | Link |
|---|
There are no public endpoints for this model yet.
Rent your own physically dedicated instance with hourly or long-term monthly billing.
We recommend deploying private instances in the following scenarios:
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
131,072.0 pipeline |
3 | $1.34 | 1.190 | Launch | ||
131,072.0 tensor |
4 | $1.62 | 1.787 | Launch | ||
131,072.0 pipeline |
6 | $1.65 | 1.631 | Launch | ||
131,072.0 tensor |
2 | $2.22 | 1.043 | Launch | ||
131,072.0 pipeline |
3 | $2.29 | 1.190 | Launch | ||
131,072.0 tensor |
4 | $2.34 | 1.787 | Launch | ||
131,072.0 |
1 | $2.37 | 1.572 | Launch | ||
131,072.0 pipeline |
3 | $2.83 | 1.190 | Launch | ||
131,072.0 tensor |
4 | $2.89 | 1.787 | Launch | ||
131,072.0 tensor |
2 | $2.93 | 1.043 | Launch | ||
131,072.0 tensor |
4 | $3.60 | 1.787 | Launch | ||
131,072.0 |
1 | $3.83 | 1.572 | Launch | ||
131,072.0 |
1 | $4.11 | 1.965 | Launch | ||
131,072.0 |
1 | $4.74 | 3.287 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
131,072.0 pipeline |
6 | $1.65 | 1.232 | Launch | ||
131,072.0 tensor |
4 | $1.75 | 1.388 | Launch | ||
131,072.0 tensor |
4 | $2.34 | 1.388 | Launch | ||
131,072.0 |
1 | $2.50 | 1.173 | Launch | ||
131,072.0 tensor |
4 | $2.97 | 1.388 | Launch | ||
131,072.0 tensor |
4 | $3.68 | 1.388 | Launch | ||
131,072.0 pipeline |
3 | $3.89 | 1.466 | Launch | ||
131,072.0 |
1 | $3.95 | 1.173 | Launch | ||
131,072.0 |
1 | $4.11 | 1.566 | Launch | ||
131,072.0 pipeline |
3 | $4.34 | 1.466 | Launch | ||
131,072.0 tensor |
4 | $4.35 | 2.288 | Launch | ||
131,072.0 |
1 | $4.74 | 2.888 | Launch | ||
131,072.0 tensor |
4 | $5.74 | 2.288 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
131,072.0 pipeline |
6 | $3.50 | 1.533 | Launch | ||
131,072.0 tensor |
8 | $4.61 | 2.727 | Launch | ||
131,072.0 tensor |
4 | $4.66 | 1.239 | Launch | ||
131,072.0 tensor |
2 | $4.67 | 2.296 | Launch | ||
131,072.0 |
1 | $4.74 | 1.839 | Launch | ||
131,072.0 tensor |
4 | $5.74 | 1.239 | Launch | ||
131,072.0 pipeline |
6 | $5.83 | 1.533 | Launch | ||
131,072.0 tensor |
8 | $7.51 | 2.727 | Launch | ||
131,072.0 tensor |
2 | $7.84 | 2.296 | Launch | ||
131,072.0 tensor |
2 | $8.17 | 3.083 | Launch | ||
Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.