Qwen3-1.7B is a model with 1.7 billion parameters that retains an architecture of 28 layers and supports a context window of 40K tokens. It uses the same attention configuration (16/8 heads) and architectural design as the smaller model in the series, but offers significantly enhanced capabilities thanks to its increased parameter count. Trained on 36 trillion tokens and supporting 119 languages, it delivers a substantial improvement in text understanding and generation quality compared to similar-sized models.
The model demonstrates strong performance in tasks requiring reasoning and contextual understanding, while maintaining high computational efficiency. Its built-in thinking and non-thinking modes allow it to adapt to different query types — from quick information retrieval to moderately complex analytical tasks. The thinking budget mechanism is especially useful for optimizing performance under variable workloads.
Qwen3-1.7B is ideally suited for desktop applications, cloud services with moderate resource requirements, and simple enterprise solutions. The model excels at document analysis, multilingual customer support, and educational applications where a balance between output quality and processing speed is essential.
| 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 | |||
|---|---|---|---|---|---|---|
40,960.0 |
1 | $0.38 | 38.03 | 2.430 | Launch | |
40,960.0 |
1 | $0.53 | 163.01 | 4.091 | Launch | |
40,960.0 |
1 | $0.57 | 225.80 | 1.381 | Launch | |
40,960.0 |
1 | $0.83 | 215.17 | 4.314 | Launch | |
40,960.0 |
1 | $1.02 | 4.306 | Launch | ||
40,960.0 tensor |
2 | $1.56 | 8.944 | Launch | ||
40,960.0 |
1 | $1.59 | 5.952 | Launch | ||
40,960.0 |
1 | $2.37 | 16.025 | Launch | ||
40,960.0 |
1 | $3.83 | 248.98 | 16.010 | Launch | |
40,960.0 |
1 | $4.11 | 18.935 | Launch | ||
40,960.0 tensor |
2 | $4.61 | 32.366 | Launch | ||
40,960.0 |
1 | $4.74 | 28.758 | Launch | ||
40,960.0 tensor |
2 | $9.40 | 57.831 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
40,960.0 |
1 | $0.38 | 59.61 | 2.368 | Launch | |
40,960.0 |
1 | $0.53 | 156.01 | 4.030 | Launch | |
40,960.0 |
1 | $0.57 | 223.50 | 1.319 | Launch | |
40,960.0 |
1 | $0.83 | 4.234 | Launch | ||
40,960.0 |
1 | $1.02 | 4.244 | Launch | ||
40,960.0 tensor |
2 | $1.56 | 8.944 | Launch | ||
40,960.0 |
1 | $1.59 | 5.891 | Launch | ||
40,960.0 |
1 | $2.37 | 253.91 | 15.963 | Launch | |
40,960.0 |
1 | $3.83 | 223.52 | 15.949 | Launch | |
40,960.0 |
1 | $4.11 | 18.874 | Launch | ||
40,960.0 tensor |
2 | $4.61 | 32.366 | Launch | ||
40,960.0 |
1 | $4.74 | 28.696 | Launch | ||
40,960.0 tensor |
2 | $9.40 | 57.831 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
40,960.0 |
1 | $0.38 | 40.80 | 1.984 | Launch | |
40,960.0 |
1 | $0.53 | 105.73 | 3.646 | Launch | |
40,960.0 |
1 | $0.83 | 174.60 | 3.869 | Launch | |
40,960.0 tensor |
2 | $0.97 | 2.606 | Launch | ||
40,960.0 |
1 | $1.02 | 206.69 | 3.860 | Launch | |
40,960.0 tensor |
2 | $1.56 | 8.473 | Launch | ||
40,960.0 |
1 | $1.59 | 5.507 | Launch | ||
40,960.0 |
1 | $2.37 | 228.70 | 15.579 | Launch | |
40,960.0 |
1 | $3.83 | 15.565 | Launch | ||
40,960.0 |
1 | $4.11 | 18.490 | Launch | ||
40,960.0 tensor |
2 | $4.61 | 31.895 | Launch | ||
40,960.0 |
1 | $4.74 | 28.312 | Launch | ||
40,960.0 tensor |
2 | $9.40 | 57.360 | Launch | ||
Contact our dedicated neural networks support team at support@immers.cloud or send your request to the sales department at sale@immers.cloud.