Qwen2.5-1.5B-Instruct

Qwen2.5-1.5B features 1.5 billion parameters, delivering significantly improved performance over the 0.5B version while maintaining relatively low computational requirements. It retains the same 32K-token context window and 8K-token generation capability, enabling support for a wide range of tasks. This preserves the key advantage of lightweight models—the balance between performance and efficiency. The model demonstrates strong capabilities in logical reasoning, contextual understanding, and coherent text generation across multiple languages (including Russian), while remaining lightweight enough for deployment on computationally constrained, power-sensitive devices.

Qwen2.5-1.5B stands out for its fast response times, versatility, and ability to operate in resource-limited environments while maintaining high-quality responses and instruction comprehension. The model is particularly well-suited for enterprise chatbots, smart assistants, on-premise support systems, as well as educational and research projects where data privacy and autonomous operation are critical.


Announce Date: 17.09.2024
Parameters: 2B
Context: 33K
Layers: 28
Attention Type: Full Attention
Developer: Qwen
Transformers Version: 4.43.1
License: Apache 2.0

Public endpoint

Use our pre-built public endpoints for free to test inference and explore Qwen2.5-1.5B-Instruct 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 Qwen2.5-1.5B-Instruct

Prices:
Name GPU Price, hour TPS Max Concurrency
teslaa2-1.16.32.240
32,768.0
1 $0.39 12.376 Launch
teslat4-1.16.64.160
32,768.0
1 $0.42 12.376 Launch
rtx2080ti-2.16.64.160
32,768.0
tensor
2 $0.71 15.690 Launch
rtx3080-2.16.64.160
32,768.0
tensor
2 $1.03 13.633 Launch
rtx4090-1.32.64.160
32,768.0
1 $1.18 20.605 Launch
rtxa5000-2.16.64.160.nvlink
32,768.0
tensor
2 $1.23 42.433 Launch
rtx5090-1.32.64.160
32,768.0
1 $1.69 28.833 Launch
teslaa10-4.16.128.160
32,768.0
tensor
4 $1.75 86.090 Launch
teslaa100-1.16.64.160
32,768.0
1 $2.37 78.205 Launch
rtx3090-4.16.128.160
32,768.0
tensor
4 $3.01 86.090 Launch
h100-1.16.64.160
32,768.0
1 $3.83 78.205 Launch
h100nvl-1.16.96.160
32,768.0
1 $4.11 92.605 Launch
teslaa100-2.24.256.160.nvlink
32,768.0
tensor
2 $4.93 157.633 Launch
h200-2.24.256.160.nvlink
32,768.0
tensor
2 $9.40 283.119 Launch
h200-4.32.768.480
32,768.0
tensor
4 $19.23 567.462 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslaa2-1.16.32.240
32,768.0
1 $0.39 11.957 Launch
teslat4-1.16.64.160
32,768.0
1 $0.42 11.957 Launch
rtx2080ti-2.16.64.160
32,768.0
tensor
2 $0.71 15.271 Launch
rtx3080-2.16.64.160
32,768.0
tensor
2 $1.03 13.214 Launch
rtx4090-1.32.64.160
32,768.0
1 $1.18 20.185 Launch
rtxa5000-2.16.64.160.nvlink
32,768.0
tensor
2 $1.23 42.014 Launch
rtx5090-1.32.64.160
32,768.0
1 $1.69 28.414 Launch
teslaa10-4.16.128.160
32,768.0
tensor
4 $1.75 85.671 Launch
teslaa100-1.16.64.160
32,768.0
1 $2.37 77.785 Launch
rtx3090-4.16.128.160
32,768.0
tensor
4 $3.01 85.671 Launch
h100-1.16.64.160
32,768.0
1 $3.83 77.785 Launch
h100nvl-1.16.96.160
32,768.0
1 $4.11 92.185 Launch
teslaa100-2.24.256.160.nvlink
32,768.0
tensor
2 $4.93 157.214 Launch
h200-2.24.256.160.nvlink
32,768.0
tensor
2 $9.40 282.700 Launch
h200-4.32.768.480
32,768.0
tensor
4 $19.23 567.043 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslaa2-1.16.32.240
32,768.0
1 $0.39 10.069 Launch
teslat4-1.16.64.160
32,768.0
1 $0.42 10.069 Launch
rtx2080ti-2.16.64.160
32,768.0
tensor
2 $0.71 13.383 Launch
rtx3080-2.16.64.160
32,768.0
tensor
2 $1.03 11.326 Launch
rtx4090-1.32.64.160
32,768.0
1 $1.18 18.297 Launch
rtxa5000-2.16.64.160.nvlink
32,768.0
tensor
2 $1.23 40.126 Launch
rtx5090-1.32.64.160
32,768.0
1 $1.69 26.526 Launch
teslaa10-4.16.128.160
32,768.0
tensor
4 $1.75 83.783 Launch
teslaa100-1.16.64.160
32,768.0
1 $2.37 75.897 Launch
rtx3090-4.16.128.160
32,768.0
tensor
4 $3.01 83.783 Launch
h100-1.16.64.160
32,768.0
1 $3.83 75.897 Launch
h100nvl-1.16.96.160
32,768.0
1 $4.11 90.297 Launch
teslaa100-2.24.256.160.nvlink
32,768.0
tensor
2 $4.93 155.326 Launch
h200-2.24.256.160.nvlink
32,768.0
tensor
2 $9.40 280.811 Launch
h200-4.32.768.480
32,768.0
tensor
4 $19.23 565.154 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.