DeepSeek-R1-Distill-Qwen-32B

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.


Announce Date: 20.01.2025
Parameters: 33B
Context: 132K
Layers: 64
Attention Type: Full or Sliding Window Attention
Developer: DeepSeek
Transformers Version: 4.43.1
License: Apache 2.0

Public endpoint

Use our pre-built public endpoints for free to test inference and explore DeepSeek-R1-Distill-Qwen-32B capabilities. You can obtain an API access token on the token management page after registration and verification.
Model Name Context Type GPU Status Link
There are no public endpoints for this model yet.

Private server

Rent your own physically dedicated instance with hourly or long-term monthly billing.

We recommend deploying private instances in the following scenarios:

  • maximize endpoint performance,
  • enable full context for long sequences,
  • ensure top-tier security for data processing in an isolated, dedicated environment,
  • use custom weights, such as fine-tuned models or LoRA adapters.

Recommended server configurations for hosting DeepSeek-R1-Distill-Qwen-32B

Prices:
Name GPU Price, hour TPS Max Concurrency
teslat4-3.32.64.200
131,072.0
pipeline
3 $0.88 0.515 Launch
rtx2080ti-4.16.64.160
131,072.0
tensor
4 $1.18 0.325 Launch
rtxa5000-2.16.64.160.nvlink
131,072.0
tensor
2 $1.23 0.593 Launch
teslaa2-4.32.128.480
131,072.0
tensor
4 $1.29 0.887 Launch
teslaa2-3.32.256.160
131,072.0
pipeline
3 $1.31 0.515 Launch
teslat4-4.48.192.320
131,072.0
tensor
4 $1.43 0.887 Launch
teslaa10-4.16.128.160
131,072.0
tensor
4 $1.75 1.787 Launch
rtx3080-4.16.96.160
131,072.0
tensor
4 $1.88 0.212 Launch
rtx4090-2.16.64.160
131,072.0
tensor
2 $1.92 0.593 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 1.572 Launch
rtx5090-2.16.64.160
131,072.0
tensor
2 $2.93 1.043 Launch
rtx3090-4.16.128.160
131,072.0
tensor
4 $3.01 1.787 Launch
h100-1.16.64.160
131,072.0
1 $3.83 1.572 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 1.965 Launch
teslaa100-2.24.256.160.nvlink
131,072.0
tensor
2 $4.93 3.743 Launch
h200-2.24.256.160.nvlink
131,072.0
tensor
2 $9.40 7.175 Launch
h200-4.32.768.480
131,072.0
tensor
4 $19.23 14.950 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslat4-3.32.64.200
131,072.0
pipeline
3 $0.88 0.116 Launch
rtx2080ti-4.16.64.160
131,072.0
tensor
4 $1.18 -0.074 Launch
rtxa5000-2.16.64.160.nvlink
131,072.0
tensor
2 $1.23 0.195 Launch
teslaa2-4.32.128.480
131,072.0
tensor
4 $1.29 0.488 Launch
teslaa2-3.32.256.160
131,072.0
pipeline
3 $1.31 0.116 Launch
teslat4-4.48.192.320
131,072.0
tensor
4 $1.43 0.488 Launch
teslaa10-4.16.128.160
131,072.0
tensor
4 $1.75 1.388 Launch
rtx3080-4.16.96.160
131,072.0
tensor
4 $1.88 -0.187 Launch
rtx4090-2.16.64.160
131,072.0
tensor
2 $1.92 0.195 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 1.173 Launch
rtx5090-2.16.64.160
131,072.0
tensor
2 $2.93 0.645 Launch
rtx3090-4.16.128.160
131,072.0
tensor
4 $3.01 1.388 Launch
h100-1.16.64.160
131,072.0
1 $3.83 1.173 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 1.566 Launch
teslaa100-2.24.256.160.nvlink
131,072.0
tensor
2 $4.93 3.345 Launch
h200-2.24.256.160.nvlink
131,072.0
tensor
2 $9.40 6.776 Launch
h200-4.32.768.480
131,072.0
tensor
4 $19.23 14.551 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslat4-3.32.64.200
131,072.0
pipeline
3 $0.88 -0.933 Launch
rtx2080ti-4.16.64.160
131,072.0
tensor
4 $1.18 -1.123 Launch
rtxa5000-2.16.64.160.nvlink
131,072.0
tensor
2 $1.23 -0.854 Launch
teslaa2-4.32.128.480
131,072.0
tensor
4 $1.29 -0.561 Launch
teslaa2-3.32.256.160
131,072.0
pipeline
3 $1.31 -0.933 Launch
teslat4-4.48.192.320
131,072.0
tensor
4 $1.43 -0.561 Launch
teslaa10-4.16.128.160
131,072.0
tensor
4 $1.75 0.339 Launch
rtx3080-4.16.96.160
131,072.0
tensor
4 $1.88 -1.236 Launch
rtx4090-2.16.64.160
131,072.0
tensor
2 $1.92 -0.854 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 0.124 Launch
rtx5090-2.16.64.160
131,072.0
tensor
2 $2.93 -0.404 Launch
rtx3090-4.16.128.160
131,072.0
tensor
4 $3.01 0.339 Launch
h100-1.16.64.160
131,072.0
1 $3.83 0.124 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 0.517 Launch
teslaa100-2.24.256.160.nvlink
131,072.0
tensor
2 $4.93 2.296 Launch
h200-2.24.256.160.nvlink
131,072.0
tensor
2 $9.40 5.727 Launch
h200-4.32.768.480
131,072.0
tensor
4 $19.23 13.502 Launch

Related models

Need help?

Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.