DeepSeek-R1-Distill-1.5B is the most compact model in the DeepSeek-R1 distilled model family, built on the Qwen2.5-1.5B architecture. Despite its small size, it has inherited fundamental reasoning skills from its teacher model — DeepSeek-R1. The model was fine-tuned on data generated by DeepSeek-R1, allowing it to significantly outperform other open-source models of similar size across multiple reasoning benchmarks.
Technically, the 1.5B version is optimized for operation on devices with limited computing resources, such as laptops, mobile devices, and edge servers. It delivers fast response times and low power consumption, making it ideal for offline applications and integration into end-user products with strict latency requirements.
In terms of use cases, DeepSeek-R1-Distill-1.5B excels at basic text analysis, short-answer generation, automation of routine tasks (such as processing customer support requests), and educational applications where a compact yet capable model is needed. Despite its size limitations, the model performs well on tasks involving simple logical operations. This makes it an excellent choice for applications where speed and minimal resource consumption are critical.
| 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 |
1 | $0.33 | 2.404 | Launch | ||
131,072.0 |
1 | $0.38 | 1.352 | Launch | ||
131,072.0 |
1 | $0.38 | 2.414 | Launch | ||
131,072.0 |
1 | $0.53 | 4.491 | Launch | ||
131,072.0 |
1 | $0.57 | 1.103 | Launch | ||
131,072.0 |
1 | $0.83 | 4.770 | Launch | ||
131,072.0 |
1 | $1.02 | 4.759 | Launch | ||
131,072.0 tensor |
2 | $1.23 | 9.462 | Launch | ||
131,072.0 |
1 | $1.59 | 6.817 | Launch | ||
131,072.0 |
1 | $2.37 | 19.408 | Launch | ||
131,072.0 |
1 | $3.83 | 19.390 | Launch | ||
131,072.0 |
1 | $4.11 | 23.046 | Launch | ||
131,072.0 tensor |
2 | $4.61 | 39.297 | Launch | ||
131,072.0 |
1 | $4.74 | 35.324 | Launch | ||
131,072.0 tensor |
2 | $9.40 | 71.129 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
131,072.0 |
1 | $0.33 | 2.287 | Launch | ||
131,072.0 |
1 | $0.38 | 1.235 | Launch | ||
131,072.0 |
1 | $0.38 | 2.297 | Launch | ||
131,072.0 |
1 | $0.53 | 4.374 | Launch | ||
131,072.0 |
1 | $0.83 | 4.653 | Launch | ||
131,072.0 tensor |
2 | $0.97 | 2.569 | Launch | ||
131,072.0 |
1 | $1.02 | 4.642 | Launch | ||
131,072.0 tensor |
2 | $1.23 | 9.345 | Launch | ||
131,072.0 |
1 | $1.59 | 6.700 | Launch | ||
131,072.0 |
1 | $2.37 | 19.291 | Launch | ||
131,072.0 |
1 | $3.83 | 19.273 | Launch | ||
131,072.0 |
1 | $4.11 | 22.929 | Launch | ||
131,072.0 tensor |
2 | $4.61 | 39.180 | Launch | ||
131,072.0 |
1 | $4.74 | 35.207 | Launch | ||
131,072.0 tensor |
2 | $9.40 | 71.012 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
131,072.0 |
1 | $0.33 | 1.939 | Launch | ||
131,072.0 |
1 | $0.38 | 1.949 | Launch | ||
131,072.0 |
1 | $0.53 | 4.026 | Launch | ||
131,072.0 tensor |
2 | $0.69 | 2.720 | Launch | ||
131,072.0 |
1 | $0.83 | 4.304 | Launch | ||
131,072.0 tensor |
2 | $0.97 | 2.221 | Launch | ||
131,072.0 |
1 | $1.02 | 4.294 | Launch | ||
131,072.0 tensor |
2 | $1.23 | 8.997 | Launch | ||
131,072.0 |
1 | $1.59 | 6.352 | Launch | ||
131,072.0 |
1 | $2.37 | 18.943 | Launch | ||
131,072.0 |
1 | $3.83 | 18.924 | Launch | ||
131,072.0 |
1 | $4.11 | 22.581 | Launch | ||
131,072.0 tensor |
2 | $4.61 | 38.831 | Launch | ||
131,072.0 |
1 | $4.74 | 34.859 | Launch | ||
131,072.0 tensor |
2 | $9.40 | 70.663 | Launch | ||
Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.