Model Library
MicrosoftReleased February 26, 2025Phi-4 Multimodal
Microsoft · Released February 26, 2025
Intelligence score
5
At a glance
- Intelligence
- 5
- Speed
- 16.8tokens/sec
- Latency
- 820mstime to first token
- Input price
- Not published
- Output price
- Not published
- Context window
- 130Ktokens
- Parameters
- 5.6billions
Summary
Comparison summary
Phi-4 Multimodal Instruct scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 6). Phi-4 Multimodal Instruct generates output at 16.8 tokens per second (based on Microsoft's API), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).
Specifications
Technical specifications
| Model name | Phi-4 Multimodal |
|---|---|
| Provider | Microsoft |
| Release date | February 26, 2025 |
| Intelligence score | 5 |
| Speed | 16.8 tokens/sec |
| Latency (TTFT) | 0.82s |
| Input price | Not published |
| Output price | Not published |
| Context window | 130,000 tokens |
| Parameters | 5.6B |
| Reasoning | No |
| Input modalities | text, image, audio |
| Output modalities | — |
| Open weights | Yes |
| License | MIT |
| API availability | — |
| Source | Model Intelligence legacy profile: phi-4-multimodal |
FAQ · 18
Frequently asked questions
Phi-4 Multimodal Instruct was released on February 26, 2025.
Phi-4 Multimodal Instruct was created by Microsoft.
Phi-4 Multimodal Instruct scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 6).
Phi-4 Multimodal Instruct generates output at 16.8 tokens per second (based on Microsoft's API), which is at the lower end compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).
Phi-4 Multimodal Instruct has a time to first token (TTFT) of 0.82s (based on Microsoft's API), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.54s).
No, Phi-4 Multimodal Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Phi-4 Multimodal Instruct supports text, image, and speech input.
Phi-4 Multimodal Instruct supports text output.
Yes, Phi-4 Multimodal Instruct supports image input and can analyze, describe, and answer questions about images.
Yes, Phi-4 Multimodal Instruct is multimodal. It can process text, image, and speech input and generate text output.
Phi-4 Multimodal Instruct has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Phi-4 Multimodal Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Phi-4 Multimodal Instruct has 5.6 billion parameters.
Phi-4 Multimodal Instruct is released under the MIT license. This license allows commercial use.
Phi-4 Multimodal Instruct achieves a score of 5 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Phi-4 Multimodal Instruct has a knowledge cutoff of June 2024. The model's training data includes information up to this date.
Yes, Phi-4 Multimodal Instruct is available via API through 1 provider.
Phi-4 Multimodal Instruct is available through 1 API provider.