Phi-3 Mini Specs, Benchmarks & Downloads
Phi-3 Mini
Microsoft compact model
Status
active
Parameters
3.80
Context Window
128000
Modality
Text
Release Date
Apr 23, 2024
About
Explore Phi-3 Mini, a text AI model developed by Microsoft. View specifications, context window, architecture, license, supported platforms, features, benchmarks, official downloads, and related articles.
Phi-3 Mini provides strong performance for local deployment.
Family
PhiDeveloper
MicrosoftArchitecture
TransformerLicense
Apache 2.0Hardware Requirements
Minimum:
Use Case: Local inference
GPU Minimum: GTX 1650
GPU VRAM: 4GB
System RAM: 8GB
Storage: 10GB
Operating System: Windows Linux
Phi-3 Mini deployment
Recommended:
Use Case: Desktop inference
GPU Minimum: RTX 3060
GPU VRAM: 12GB
System RAM: 16GB
Storage: 20GB
Operating System: Linux
Recommended setup
High Performance:
Use Case: Fast inference
GPU Minimum: RTX 4070
GPU VRAM: 12GB
System RAM: 32GB
Storage: 30GB
Operating System: Linux
High throughput
Model Deployment Readiness
Model Ecosystem Support
18%
Platforms
33%
Features
1%
Downloads
20%
Platform Compatibility
33%
Supported across 4 of 12 platforms
Context Window
Industry-standard context window comparison
128,000
tokens
125K
4K
32K
128K
1M
2M
Database Rank
#17
Percentile
Top 84%
Capacity
High
Benchmark Performance
Evaluation profile across publicly reported benchmarks
|
MMLU
|
Knowledge | 68.8 % | 2024 |
|
GPQA
|
Reasoning | 30.9 % | 2024 |
|
HumanEval
|
Coding | 57.3 % | 2024 |
|
MATH-500
|
Mathematics | 50.3 % | 2024 |
|
GSM8K
|
Mathematics | 86.3 % | 2024 |
|
HellaSwag
|
Reasoning | 76.2 % | 2024 |
|
HumanEval
|
Coding | 59.1 % | 2024 |
Highest Benchmark
GSM8K
86.3%
Benchmarks Available
7
Latest Evaluation
Apr 2024
