Phi-4-multimodal-instruct

multimodal

Phi-4-multimodal-instruct is an open-source multimodal model from Microsoft that processes text, images, and audio in a unified architectural solution. It builds upon the Phi-3.5 and Phi-4.0 technologies, featuring an extended context window of 128K tokens and support for 23 languages in text (including Russian), 8 languages in audio, and English for visual tasks. The model is optimized for environments with limited computational resources and low-latency scenarios, demonstrating strong performance in mathematics, logic, speech recognition, translation, and image analysis.  

A single neural network handles text, images (OCR, tables, diagrams), and audio (recognition, translation, summarization). For example, in DocVQA benchmarks, the model achieves 93.2% accuracy, outperforming Gemini-2.0-Flash (92.1%).  

The model is ideal for multisensory applications—joint processing of audio and images (e.g., video analysis with subtitles). At the same time, thanks to optimization via Microsoft Olive and ONNX GenAI Runtime, it can be deployed on edge devices, including smartphones and IoT systems, even with limited computational resources.


Announce Date: 27.02.2025
Parameters: 6B
Context: 132K
Layers: 32
Attention Type: Full Attention
Developer: Microsoft
Transformers Version: 4.46.1
License: MIT

Public endpoint

Use our pre-built public endpoints for free to test inference and explore Phi-4-multimodal-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 Phi-4-multimodal-instruct

Prices:
Name GPU Price, hour TPS Max Concurrency
teslaa10-2.16.64.160
131,072.0
tensor
2 $0.93 1.414 Launch
teslaa2-3.32.128.160
131,072.0
pipeline
3 $1.06 1.075 Launch
teslaa2-4.32.128.160
131,072.0
tensor
4 $1.26 1.757 Launch
rtx3090-2.16.64.160
131,072.0
tensor
2 $1.56 1.536 Launch
rtx3090-2.16.64.160.nvlink
131,072.0
tensor
2 $1.56 1.536 Launch
rtx4090-2.16.64.160
131,072.0
tensor
2 $1.92 1.532 Launch
teslaa100-1.16.64.160
131,072.0
1 $2.37 3.597 Launch
rtx5090-2.16.64.160
131,072.0
tensor
2 $2.93 2.432 Launch
h100-1.16.64.160
131,072.0
1 $3.83 3.593 Launch
h100nvl-1.16.96.160
131,072.0
1 $4.11 4.393 Launch
teslaa100-2.24.96.160.nvlink
131,072.0
tensor
2 $4.61 7.941 Launch
h200-1.16.128.160
131,072.0
1 $4.74 7.079 Launch
h200-2.24.256.160.nvlink
131,072.0
tensor
2 $9.40 14.904 Launch

Related models

Need help?

Contact our dedicated neural networks support team at support@immers.cloud or send your request to the sales department at sale@immers.cloud.

We use cookies and web analytics services to ensure the proper functioning of the website, analyze web-site traffic, and improve the quality of our services.
By continuing to use the website, you consent to the Privacy Policy and consent to the processing of cookie files and technical data.