Empowering innovation: The following era of the Phi household

We’re excited to announce Phi-4-multimodal and Phi-4-mini, the latest fashions in Microsoft’s Phi household of small language fashions (SLMs). These fashions are designed to empower builders with superior AI capabilities.

We’re excited to announce Phi-4-multimodal and Phi-4-mini, the latest fashions in Microsoft’s Phi household of small language fashions (SLMs). These fashions are designed to empower builders with superior AI capabilities. Phi-4-multimodal, with its capacity to course of speech, imaginative and prescient, and textual content concurrently, opens new potentialities for creating revolutionary and context-aware functions. Phi-4-mini, however, excels in text-based duties, offering excessive accuracy and scalability in a compact kind. Now out there in Azure AI Foundry, HuggingFace, and the NVIDIA API Catalog the place builders can discover the total potential of Phi-4-multimodal on the NVIDIA API Catalog, enabling them to experiment and innovate with ease. 

What’s Phi-4-multimodal?

Phi-4-multimodal marks a brand new milestone in Microsoft’s AI improvement as our first multimodal language mannequin. On the core of innovation lies steady enchancment, and that begins with listening to our prospects. In direct response to buyer suggestions, we’ve developed Phi-4-multimodal, a 5.6B parameter mannequin, that seamlessly integrates speech, imaginative and prescient, and textual content processing right into a single, unified structure.

By leveraging superior cross-modal studying methods, this mannequin permits extra pure and context-aware interactions, permitting gadgets to know and cause throughout a number of enter modalities concurrently. Whether or not deciphering spoken language, analyzing pictures, or processing textual data, it delivers extremely environment friendly, low-latency inference—all whereas optimizing for on-device execution and diminished computational overhead.

Natively constructed for multimodal experiences

Phi-4-multimodal is a single mannequin with mixture-of-LoRAs that features speech, imaginative and prescient, and language, all processed concurrently throughout the similar illustration area. The result’s a single, unified mannequin able to dealing with textual content, audio, and visible inputs—no want for advanced pipelines or separate fashions for various modalities.

The Phi-4-multimodal is constructed on a brand new structure that enhances effectivity and scalability. It incorporates a bigger vocabulary for improved processing, helps multilingual capabilities, and integrates language reasoning with multimodal inputs. All of that is achieved inside a strong, compact, extremely environment friendly mannequin that’s suited to deployment on gadgets and edge computing platforms.

This mannequin represents a step ahead for the Phi household of fashions, providing enhanced efficiency in a small bundle. Whether or not you’re in search of superior AI capabilities on cell gadgets or edge methods, Phi-4-multimodal offers a high-capability possibility that’s each environment friendly and versatile.

Unlocking new capabilities

With its elevated vary of capabilities and suppleness, Phi-4-multimodal opens thrilling new potentialities for app builders, companies, and industries trying to harness the ability of AI in revolutionary methods. The way forward for multimodal AI is right here, and it’s prepared to remodel your functions.

Phi-4-multimodal is able to processing each visible and audio collectively. The next desk reveals the mannequin high quality when the enter question for imaginative and prescient content material is artificial speech on chart/desk understanding and doc reasoning duties. In comparison with different present state-of-the-art omni fashions that may allow audio and visible alerts as enter, Phi-4-multimodal achieves a lot stronger efficiency on a number of benchmarks.

Phi-4-multimodal has demonstrated exceptional capabilities in speech-related duties, rising as a number one open mannequin in a number of areas. It outperforms specialised fashions like WhisperV3 and SeamlessM4T-v2-Massive in each automated speech recognition (ASR) and speech translation (ST). The mannequin has claimed the highest place on the Huggingface OpenASR leaderboard with a powerful phrase error charge of 6.14%, surpassing the earlier greatest efficiency of 6.5% as of February 2025. Moreover, it’s amongst a number of open fashions to efficiently implement speech summarization and obtain efficiency ranges akin to GPT-4o mannequin. The mannequin has a spot with shut fashions, comparable to Gemini-2.0-Flash and GPT-4o-realtime-preview, on speech query answering (QA) duties because the smaller mannequin measurement leads to much less capability to retain factual QA data. Work is being undertaken to enhance this functionality within the subsequent iterations.

Phi-4-multimodal with solely 5.6B parameters demonstrates exceptional imaginative and prescient capabilities throughout varied benchmarks, most notably reaching sturdy efficiency on mathematical and science reasoning. Regardless of its smaller measurement, the mannequin maintains aggressive efficiency on normal multimodal capabilities, comparable to doc and chart understanding, Optical Character Recognition (OCR), and visible science reasoning, matching or exceeding shut fashions like Gemini-2-Flash-lite-preview/Claude-3.5-Sonnet.

What’s Phi-4-mini?

Phi-4-mini is a 3.8B parameter mannequin and a dense, decoder-only transformer that includes grouped-query consideration, 200,000 vocabulary, and shared input-output embeddings, designed for velocity and effectivity. Regardless of its compact measurement, it continues outperforming bigger fashions in text-based duties, together with reasoning, math, coding, instruction-following, and function-calling. Supporting sequences as much as 128,000 tokens, it delivers excessive accuracy and scalability, making it a strong answer for superior AI functions.

To grasp the mannequin high quality, we evaluate Phi-4-mini with a set of fashions over a wide range of benchmarks as proven in Determine 4.

Operate calling, instruction following, lengthy context, and reasoning are highly effective capabilities that allow small language fashions like Phi-4-mini to entry exterior data and performance regardless of their restricted capability. Via a standardized protocol, perform calling permits the mannequin to seamlessly combine with structured programming interfaces. When a person makes a request, Phi-4-Mini can cause by way of the question, determine and name related features with applicable parameters, obtain the perform outputs, and incorporate these outcomes into its responses. This creates an extensible agentic-based system the place the mannequin’s capabilities could be enhanced by connecting it to exterior instruments, software program interfaces (APIs), and information sources by way of well-defined perform interfaces. The next instance simulates a sensible dwelling management agent with Phi-4-mini.

At Headwaters, we’re leveraging fine-tuned SLM like Phi-4-mini on the sting to boost operational effectivity and supply revolutionary options. Edge AI demonstrates excellent efficiency even in environments with unstable community connections or in fields the place confidentiality is paramount. This makes it extremely promising for driving innovation throughout varied industries, together with anomaly detection in manufacturing, fast diagnostic help in healthcare, and enhancing buyer experiences in retail. We’re trying ahead to delivering new options within the AI agent period with Phi-4 mini.
 
—Masaya Nishimaki, Firm Director, Headwaters Co., Ltd. 

Customization and cross-platform

Due to their smaller sizes, Phi-4-mini and Phi-4-multimodal fashions can be utilized in compute-constrained inference environments. These fashions can be utilized on-device, particularly when additional optimized with ONNX Runtime for cross-platform availability. Their decrease computational wants make them a decrease price possibility with significantly better latency. The longer context window permits taking in and reasoning over massive textual content content material—paperwork, net pages, code, and extra. Phi-4-mini and multimodal demonstrates sturdy reasoning and logic capabilities, making it a great candidate for analytical duties. Their small measurement additionally makes fine-tuning or customization simpler and extra reasonably priced. The desk under reveals examples of finetuning situations with Phi-4-multimodal.

For extra details about customization or to study extra in regards to the fashions, check out Phi Cookbook on GitHub. 

How can these fashions be utilized in motion?

These fashions are designed to deal with advanced duties effectively, making them splendid for edge case situations and compute-constrained environments. Given the brand new capabilities Phi-4-multimodal and Phi-4-mini deliver, the makes use of of Phi are solely increasing. Phi fashions are being embedded into AI ecosystems and used to discover varied use circumstances throughout industries.

Language fashions are highly effective reasoning engines, and integrating small language fashions like Phi into Home windows permits us to keep up environment friendly compute capabilities and opens the door to a way forward for steady intelligence baked in throughout all of your apps and experiences. Copilot+ PCs will construct upon Phi-4-multimodal’s capabilities, delivering the ability of Microsoft’s superior SLMs with out the power drain. This integration will improve productiveness, creativity, and education-focused experiences, changing into a typical a part of our developer platform.

—Vivek Pradeep, Vice President Distinguished Engineer of Home windows Utilized Sciences.

1. Embedded on to your good machine: Telephone producers integrating Phi-4-multimodal immediately right into a smartphone may allow smartphones to course of and perceive voice instructions, acknowledge pictures, and interpret textual content seamlessly. Customers may gain advantage from superior options like real-time language translation, enhanced photograph and video evaluation, and clever private assistants that perceive and reply to advanced queries. This is able to elevate the person expertise by offering highly effective AI capabilities immediately on the machine, making certain low latency and excessive effectivity.
2. On the street: Think about an automotive firm integrating Phi-4-multimodal into their in-car assistant methods. The mannequin may allow autos to know and reply to voice instructions, acknowledge driver gestures, and analyze visible inputs from cameras. For example, it may improve driver security by detecting drowsiness by way of facial recognition and offering real-time alerts. Moreover, it may supply seamless navigation help, interpret street indicators, and supply contextual data, making a extra intuitive and safer driving expertise whereas related to the cloud and offline when connectivity isn’t out there.
3. Multilingual monetary companies: Think about a monetary companies firm integrating Phi-4-mini to automate advanced monetary calculations, generate detailed reviews, and translate monetary paperwork into a number of languages. For example, the mannequin can help analysts by performing intricate mathematical computations required for threat assessments, portfolio administration, and monetary forecasting. Moreover, it might translate monetary statements, regulatory paperwork, and consumer communications into varied languages and will enhance consumer relations globally.

Microsoft’s dedication to safety and security

Azure AI Foundry offers customers with a sturdy set of capabilities to assist organizations measure, mitigate, and handle AI dangers throughout the AI improvement lifecycle for conventional machine studying and generative AI functions. Azure AI evaluations in AI Foundry allow builders to iteratively assess the standard and security of fashions and functions utilizing built-in and customized metrics to tell mitigations.

Each fashions underwent safety and security testing by our inner and exterior safety specialists utilizing methods crafted by Microsoft AI Purple Crew (AIRT). These strategies, developed over earlier Phi fashions, incorporate international views and native audio system of all supported languages. They span areas comparable to cybersecurity, nationwide safety, equity, and violence, addressing present traits by way of multilingual probing. Utilizing AIRT’s open-source Python Danger Identification Toolkit (PyRIT) and handbook probing, purple teamers carried out single-turn and multi-turn assaults. Working independently from the event groups, AIRT constantly shared insights with the mannequin staff. This method assessed the brand new AI safety and security panorama launched by our newest Phi fashions, making certain the supply of high-quality capabilities.

Check out the mannequin playing cards for Phi-4-multimodal and Phi-4-mini, and the technical paper to see an overview of really helpful makes use of and limitations for these fashions.

Study extra about Phi-4

We invite you to return discover the probabilities with Phi-4-multimodal and Phi-4-mini in Azure AI Foundry, Hugging Face, and NVIDIA API Catalog with a full multimodal expertise. We are able to’t wait to listen to your suggestions and see the unbelievable issues you’ll accomplish with our new fashions.