Phi-3 Small Specs, Benchmarks & Downloads
Phi-3 Small
Microsoft small language model
Status
active
Parameters
7.00
Context Window
128000
Modality
Text
Release Date
Apr 23, 2024
About
Explore Phi-3 Small, a text AI model developed by Microsoft. View specifications, context window, architecture, license, supported platforms, features, benchmarks, official downloads, and related articles.
Phi-3 Small improves reasoning and coding capability.
Family
PhiDeveloper
MicrosoftArchitecture
TransformerLicense
Apache 2.0Hardware Requirements
Minimum:
Use Case: Local inference
GPU Minimum: RTX 3060
GPU VRAM: 12GB
System RAM: 16GB
Storage: 20GB
Operating System: Linux
Phi-3 Small deployment
Recommended:
Use Case: Desktop inference
GPU Minimum: RTX 4070
GPU VRAM: 12GB
System RAM: 32GB
Storage: 30GB
Operating System: Linux
Recommended deployment
High Performance:
Use Case: Fast inference
GPU Minimum: RTX 4090
GPU VRAM: 24GB
System RAM: 64GB
Storage: 50GB
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 | 75.7 % | 2024 |
|
GPQA
|
Reasoning | 37.5 % | 2024 |
|
HumanEval
|
Coding | 60.4 % | 2024 |
|
MATH-500
|
Mathematics | 52.2 % | 2024 |
|
GSM8K
|
Mathematics | 86.7 % | 2024 |
|
MMLU
|
Knowledge | 71.9 % | 2024 |
|
HumanEval
|
Coding | 62.2 % | 2024 |
Highest Benchmark
GSM8K
86.7%
Benchmarks Available
7
Latest Evaluation
Apr 2024
