Qwen2-7B-Instruct

Qwen2-7B is a fully functional language model with 7 billion parameters, designed to deliver high performance across a wide range of tasks. The model features 28 layers, utilizes 28 attention heads in total with 4 key-value heads, striking an optimal balance between performance and memory efficiency. Its architecture incorporates all modern enhancements, including Grouped Query Attention (GQA), Dual Chunk Attention with YARN, and optimized Rotary Positional Embedding (RoPE) mechanisms.

Trained on the same high-quality 7-trillion-token dataset as larger models in the series, Qwen2-7B delivers strong performance across diverse knowledge domains and achieves competitive results on standard benchmarks. It supports an extended context window of 128K tokens and demonstrates exceptional multilingual capabilities.

A key advantage of Qwen2-7B is its ability to run efficiently on mid-range GPUs, making advanced AI capabilities accessible to a broader range of users and organizations. The model is well-suited for application development, large document analysis, research, and educational purposes. Additionally, it serves as an excellent base model for fine-tuning on domain-specific tasks, offering a strong trade-off between capability and resource requirements.


Announce Date: 24.07.2024
Parameters: 7B
Context: 33K
Layers: 28
Attention Type: Full Attention
Developer: Qwen
Transformers Version: 4.41.2
License: Apache 2.0

Public endpoint

Use our pre-built public endpoints for free to test inference and explore Qwen2-7B-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 Qwen2-7B-Instruct

Prices:
Name GPU Price, hour TPS Max Concurrency
teslat4-1.16.16.160
32,768.0
1 $0.33 3.906 Launch
rtx2080ti-1.10.16.500
32,768.0
1 $0.38 1.803 Launch
teslaa2-1.16.32.160
32,768.0
1 $0.38 3.927 Launch
teslaa10-1.16.32.160
32,768.0
1 $0.53 8.080 Launch
rtx3080-1.16.32.160
32,768.0
1 $0.57 1.304 Launch
rtx3090-1.16.24.160
32,768.0
1 $0.83 8.637 Launch
rtx4090-1.16.32.160
32,768.0
1 $1.02 8.616 Launch
rtxa5000-2.16.64.160.nvlink
32,768.0
tensor
2 $1.23 18.023 Launch
rtx5090-1.16.64.160
32,768.0
1 $1.59 12.733 Launch
teslaa100-1.16.64.160
32,768.0
1 $2.37 37.914 Launch
h100-1.16.64.160
32,768.0
1 $3.83 37.878 Launch
h100nvl-1.16.96.160
32,768.0
1 $4.11 45.190 Launch
teslaa100-2.24.96.160.nvlink
32,768.0
tensor
2 $4.61 77.692 Launch
h200-1.16.128.160
32,768.0
1 $4.74 69.746 Launch
h200-2.24.256.160.nvlink
32,768.0
tensor
2 $9.40 141.356 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslat4-1.16.16.160
32,768.0
1 $0.33 2.043 Launch
teslaa2-1.16.32.160
32,768.0
1 $0.38 2.064 Launch
teslaa10-1.16.32.160
32,768.0
1 $0.53 6.218 Launch
rtx2080ti-2.12.64.160
32,768.0
tensor
2 $0.69 3.606 Launch
rtx3090-1.16.24.160
32,768.0
1 $0.83 6.775 Launch
rtx3080-2.16.32.160
32,768.0
tensor
2 $0.97 2.608 Launch
rtx4090-1.16.32.160
32,768.0
1 $1.02 6.754 Launch
rtxa5000-2.16.64.160.nvlink
32,768.0
tensor
2 $1.23 16.160 Launch
rtx5090-1.16.64.160
32,768.0
1 $1.59 10.870 Launch
teslaa100-1.16.64.160
32,768.0
1 $2.37 36.052 Launch
h100-1.16.64.160
32,768.0
1 $3.83 36.015 Launch
h100nvl-1.16.96.160
32,768.0
1 $4.11 43.328 Launch
teslaa100-2.24.96.160.nvlink
32,768.0
tensor
2 $4.61 75.829 Launch
h200-1.16.128.160
32,768.0
1 $4.74 67.884 Launch
h200-2.24.256.160.nvlink
32,768.0
tensor
2 $9.40 139.493 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslaa10-1.16.32.160
32,768.0
1 $0.53 1.837 Launch
teslat4-2.16.32.160
32,768.0
tensor
2 $0.54 3.432 Launch
teslaa2-2.16.32.160
32,768.0
tensor
2 $0.57 3.474 Launch
rtx3090-1.16.24.160
32,768.0
1 $0.83 2.394 Launch
rtx2080ti-3.12.24.120
32,768.0
pipeline
3 $0.84 2.313 Launch
rtx4090-1.16.32.160
32,768.0
1 $1.02 2.373 Launch
rtx2080ti-4.16.32.160
32,768.0
tensor
4 $1.12 6.557 Launch
rtxa5000-2.16.64.160.nvlink
32,768.0
tensor
2 $1.23 11.780 Launch
rtx5090-1.16.64.160
32,768.0
1 $1.59 6.490 Launch
rtx3080-4.16.64.160
32,768.0
tensor
4 $1.82 4.560 Launch
teslaa100-1.16.64.160
32,768.0
1 $2.37 31.671 Launch
h100-1.16.64.160
32,768.0
1 $3.83 31.634 Launch
h100nvl-1.16.96.160
32,768.0
1 $4.11 38.947 Launch
teslaa100-2.24.96.160.nvlink
32,768.0
tensor
2 $4.61 71.448 Launch
h200-1.16.128.160
32,768.0
1 $4.74 63.503 Launch
h200-2.24.256.160.nvlink
32,768.0
tensor
2 $9.40 135.112 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.