Phi-4-Mini
Parameters
3.8B
Context Length
128K
Modality
Text
Architecture
Dense
KV Cache Rate
128 KB/tok
License
MIT
Release Date
27 Feb 2025
Knowledge Cutoff
Jun 2024
API Pricing (per 1M)
Input: $0.07 · Output: $0.30
Hardware & System Requirements
Precision
Context
Workload Memory: 5.27 GB
INT4 · 8K context
Base Weights: 1.77 GB
KV Cache: 1.00 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
5.3 / 21.6 GB usable
1x RTX 3060 12GB
5.3 / 10.8 GB usable
Apple M4 24GB
5.3 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
Evaluation Benchmarks
Rank
#222
| Benchmark | Score | Rank |
|---|---|---|
Professional Knowledge | 0.528 | 57 |
Graduate-Level QA | 0.252 | 123 |
Coding Index | 0.04 | 155 |
Intelligence Index | 0.06 | 294 |
General Knowledge Reference | 0.673 | 28 |
Rankings
Overall Rank
#222
Coding Rank
#166
About Phi-4-Mini
Phi-4-Mini is a compact 3.8B open model from Microsoft optimized for low-latency reasoning, function calling, and edge deployment via ONNX. It features an expanded 200K vocabulary and LongRoPE context management for on-device AI.
Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
24
Key-Value Heads
8
Position Embedding
ROPE
RoPE Theta
10,000
Sliding Window Attention
Yes
Sliding Window Size
262,144
Normalization
RMS Normalization
Activation Function
Swish
Dimensions
Base Precision
BF16
Hidden Dimension Size
3,072
Number of Layers
32
FFN Intermediate Size (Dense)
8,192
Tokenizer
Vocabulary Size
200,064
About Phi-4
The Microsoft Phi-4 model family comprises small language models prioritizing efficient, high-capability reasoning. Its development emphasizes robust data quality and sophisticated synthetic data integration. This approach enables enhanced performance and on-device deployment capabilities.