Plain-English Summary
A smaller Phi-4 model for efficient local and edge text applications with long context.
Phi-4-mini-instruct
A smaller Phi-4 model for efficient local and edge text applications with long context.
Phi-4
General LLM
GA / open weights
Open weights: Yes
API: Yes and self-hosted
Technical Notes
Compact dense text model with 131K input context and 4K output, optimized for instruction following.
Best For
On-device assistants, extraction, classification, private RAG
Watch Out For
Lower reasoning and knowledge capacity than full Phi-4.
Model Specs
- Maker
- Microsoft
- Country
- USA
- Family
- Phi-4
- Type
- General LLM
- Release date
- 2025-02-26
- Date confidence
- Exact
- Status
- GA / open weights
- Context window
- 131,072 tokens
- Max output
- 4,096
- Parameters
- 3.8B
- Active parameters
- 3.8B
- Architecture
- Dense transformer
- Reasoning
- General reasoning
- Tool calling
- Host dependent
- Structured output
- Host dependent
- API available
- Yes and self-hosted
- Open weights
- Yes
- Self-hostable
- Yes
- License
- MIT
- Inputs
- Text
- Outputs
- Text
- Approx. price
- See provider pricing
- How to access
- Provider website
- Model / API ID
- Phi-4-mini-instruct
- Knowledge cutoff
- Not publicly disclosed
- Fine-tuning
- Fine-tuning, quantization, edge deployment
- Completeness
- 100 %
- Verified
- Jul 18, 2026
- Snapshot date
- Jul 18, 2026
- Source
- Official source