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

API access to DeepSeek-R1-Distill-Qwen-32B endpoints

There are no public endpoints for this model yet.

Private endpoint

An endpoint is a server with pre-installed software that automatically downloads neural network weights and launches an OpenAI-compatible API to handle incoming requests.

A private endpoint is created within the user's project, belongs exclusively to the user, and is billed per server configuration in accordance with the infrastructure pricing.

We recommend creating private endpoints when you need to:

  • achieve maximum endpoint performance,
  • access the full context window for processing large requests and conversations,
  • ensure maximum security by processing data in a dedicated, isolated environment.

Recommended server configurations for creating a private inference endpoint DeepSeek-R1-Distill-Qwen-32B

Prices:
Name GPU Price, hour TPS Max Concurrency
teslaa10-3.16.96.160
131,072.0
pipeline
3 $1.34 1.068 Launch
teslaa10-4.16.64.160
131,072.0
tensor
4 $1.62 1.697 Launch
teslaa2-6.32.128.160
131,072.0
pipeline
6 $1.65 1.424 Launch
rtx3090-3.16.96.160
131,072.0
pipeline
3 $2.29 31.19 1.157 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 1.599 Launch
rtx4090-3.16.96.160
131,072.0
pipeline
3 $2.83 1.154 Launch
rtx3090-4.16.64.160
131,072.0
tensor
4 $2.89 1.819 Launch
rtx5090-2.16.64.160
131,072.0
tensor
2 $2.93 1.053 Launch
rtx3090-4.16.128.160.nvlink
131,072.0
tensor
4 $3.01 1.819 Launch
rtx4090-4.16.64.160
131,072.0
tensor
4 $3.60 1.814 Launch
h100-1.16.64.160
131,072.0
1 $3.83 1.597 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 1.997 Launch
teslaa100-2.24.96.160.nvlink
131,072.0
tensor
2 $4.61 3.807 Launch
h200-1.16.128.160
131,072.0
1 $4.74 3.340 Launch
h200-2.24.256.160.nvlink
131,072.0
tensor
2 $9.40 7.289 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslaa10-4.16.128.160
131,072.0
tensor
4 $1.75 1.264 Launch
teslaa100-1.16.128.160
131,072.0
1 $2.50 41.46 1.192 Launch
rtx3090-4.16.96.320
131,072.0
tensor
4 $2.97 60.61 1.141 Launch
rtx3090-4.16.128.160.nvlink
131,072.0
tensor
4 $3.01 1.141 Launch
rtx4090-4.16.96.240
131,072.0
tensor
4 $3.67 1.029 Launch
h100-1.16.128.160
131,072.0
1 $3.95 1.190 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 1.590 Launch
rtx5090-3.16.96.160
131,072.0
pipeline
3 $4.34 1.385 Launch
teslaa100-2.24.96.160.nvlink
131,072.0
tensor
2 $4.61 3.392 Launch
h200-1.16.128.160
131,072.0
1 $4.74 2.933 Launch
rtx5090-4.16.128.160
131,072.0
tensor
4 $5.74 2.282 Launch
h200-2.24.256.160.nvlink
131,072.0
tensor
2 $9.40 6.873 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
h200-1.16.128.240
131,072.0
1 $4.74 2.005 Launch
teslaa100-2.24.256.240
131,072.0
tensor
2 $4.93 2.436 Launch
teslaa100-2.24.256.320.nvlink
131,072.0
tensor
2 $4.94 2.436 Launch
rtx5090-4.16.128.320
131,072.0
tensor
4 $5.76 1.271 Launch
rtx4090-6.44.256.240
131,072.0
pipeline
6 $5.84 1.405 Launch
dedicated-rtx3090-8.64.128.960-1
131,072.0
tensor
8 $6.04 2.657 Launch
rtx4090-8.44.256.240
131,072.0
tensor
8 $7.52 2.647 Launch
h100-2.24.256.240
131,072.0
tensor
2 $7.85 2.432 Launch
h100nvl-2.24.192.240
131,072.0
tensor
2 $8.17 3.232 Launch
h200-2.24.256.240.nvlink
131,072.0
tensor
2 $9.41 5.918 Launch

Related models

Need help?

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

We use cookies and web analytics services to ensure the proper functioning of the website, analyze web-site traffic, and improve the quality of our services.
By continuing to use the website, you consent to the Privacy Policy and consent to the processing of cookie files and technical data.