Llama 4 Scout is the lightest model in the next generation of the Llama 4 family, released on April 5, 2025. Llama 4 scout has a MoE architecture of 16 experts, 109 billion of which only 17 billion are permanently active. The model supports native multimodality. It is capable of simultaneously processing text and up to 5 images as input, allowing it to be used effectively in computer vision tasks such as object recognition, image description, and image-based question answering. Creative text generation, step-by-step reasoning, and programming are also among the model's strengths
That said, Llama scout can run efficiently on just a single H100 GPU, making it attractive for local deployment, and with more parameters, Llama scout outperforms lighter weight models in the segment on benchmarks.
But perhaps the most important feature of the model is its record-breaking context window support of up to 10 million tokens! which makes it ideal for working with large documents, code, multi-page queries and lengthy dialog sessions.
| 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 | |||
|---|---|---|---|---|---|---|
250,000.0 |
1 | $4.74 | 2.774 | Launch | ||
250,000.0 tensor |
2 | $4.93 | 54.27 | 4.170 | Launch | |
250,000.0 tensor |
2 | $4.94 | 4.170 | Launch | ||
250,000.0 tensor |
4 | $5.76 | 1.308 | Launch | ||
250,000.0 pipeline |
6 | $5.84 | 30.03 | 1.721 | Launch | |
250,000.0 tensor |
8 | $6.04 | 4.642 | Launch | ||
250,000.0 tensor |
8 | $7.52 | 4.619 | Launch | ||
250,000.0 tensor |
2 | $7.85 | 61.60 | 4.836 | Launch | |
250,000.0 tensor |
2 | $8.17 | 5.413 | Launch | ||
250,000.0 tensor |
2 | $9.41 | 11.213 | Launch | ||
10,485,760.0 pipeline |
6 | $28.36 | 1.366 | Launch | ||
10,485,760.0 tensor |
8 | $37.34 | 1.896 | Launch | ||
10,485,760.0 tensor |
8 | $37.34 | 1.896 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
250,000.0 |
1 | $4.74 | 2.871 | Launch | ||
250,000.0 tensor |
8 | $7.52 | 49.91 | 6.370 | Launch | |
250,000.0 tensor |
2 | $7.85 | 68.07 | 4.714 | Launch | |
250,000.0 tensor |
2 | $8.17 | 8.168 | Launch | ||
250,000.0 pipeline |
6 | $8.86 | 6.819 | Launch | ||
250,000.0 tensor |
2 | $9.41 | 113.64 | 19.767 | Launch | |
250,000.0 tensor |
8 | $11.55 | 15.147 | Launch | ||
10,485,760.0 pipeline |
6 | $28.36 | 2.653 | Launch | ||
10,485,760.0 tensor |
8 | $37.34 | 3.714 | Launch | ||
10,485,760.0 tensor |
8 | $37.34 | 3.714 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
250,000.0 tensor |
4 | $9.17 | 5.757 | Launch | ||
250,000.0 tensor |
2 | $9.42 | 3.241 | Launch | ||
250,000.0 tensor |
2 | $9.42 | 3.241 | Launch | ||
250,000.0 tensor |
4 | $9.50 | 5.757 | Launch | ||
250,000.0 pipeline |
3 | $12.38 | 2.779 | Launch | ||
250,000.0 tensor |
4 | $14.97 | 5.084 | Launch | ||
250,000.0 tensor |
4 | $16.22 | 8.538 | Launch | ||
10,485,760.0 pipeline |
6 | $28.36 | 1.125 | Launch | ||
10,485,760.0 tensor |
8 | $37.34 | 1.653 | Launch | ||
10,485,760.0 tensor |
8 | $37.34 | 1.653 | Launch | ||
Contact our dedicated neural networks support team at support@immers.cloud or send your request to the sales department at sale@immers.cloud.