Qwen2-1.5B is a lightweight model with 1.5 billion parameters, offering an optimal balance between performance and resource efficiency. The model includes 28 layers and employs Grouped Query Attention (GQA) with 12 query heads and 2 shared key-value heads, enabling efficient management of the KV-cache memory.
Trained on 7 trillion tokens of high-quality multilingual data, the model demonstrates significantly enhanced capabilities compared to previous versions, particularly in programming and mathematics. It supports a wide range of languages and delivers competitive results on standard benchmarks, while maintaining relatively low computational resource requirements.
Qwen2-1.5B stands out for its versatility and ability to perform efficiently on both consumer-grade hardware and small servers. The model supports a context window of 32K tokens, allowing it to process long documents and support complex conversations. It is ideally suited for information extraction, document analysis, entry-level programming tasks, educational applications, and enterprise chatbots. Qwen2-1.5B is an excellent choice for users seeking a reliable language model for simple tasks without the need for expensive GPU infrastructure.
| Model Name | Context | Type | GPU | Status | Link |
|---|
There are no public endpoints for this model yet.
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:
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
32,768.0 |
1 | $0.38 | 46.79 | 10.848 | Launch | |
32,768.0 |
1 | $0.53 | 108.23 | 19.063 | Launch | |
32,768.0 |
1 | $0.57 | 152.43 | 5.556 | Launch | |
32,768.0 |
1 | $0.83 | 293.00 | 20.200 | Launch | |
32,768.0 |
1 | $1.02 | 189.44 | 20.181 | Launch | |
32,768.0 tensor |
2 | $1.56 | 43.852 | Launch | ||
32,768.0 |
1 | $1.59 | 28.414 | Launch | ||
32,768.0 |
1 | $2.37 | 183.47 | 78.777 | Launch | |
32,768.0 |
1 | $3.83 | 78.704 | Launch | ||
32,768.0 |
1 | $4.11 | 93.329 | Launch | ||
32,768.0 tensor |
2 | $4.61 | 160.960 | Launch | ||
32,768.0 |
1 | $4.74 | 142.441 | Launch | ||
32,768.0 tensor |
2 | $9.40 | 288.288 | Launch | ||
Contact our dedicated neural networks support team at support@immers.cloud or send your request to the sales department at sale@immers.cloud.