ModelLLMsv3.5

Phi-3.5-mini

by Microsoft · free · Last verified 2026-03-17

Phi-3.5-mini is a 3.8B parameter instruction-tuned model from Microsoft, optimized for edge and mobile devices. Despite its compact size, it delivers performance comparable to much larger models on benchmarks for reasoning, coding, and language tasks, making it highly efficient for on-device AI applications.

https://huggingface.co/microsoft/Phi-3.5-mini-instruct ↗

B—Above Average

Adoption: B+Quality: AFreshness: ACitations: B+Engagement: F

Specifications

License: MIT
Pricing: free
Capabilities: text-generation, instruction-following, code-generation, logical-reasoning, natural-language-understanding, on-device-inference, low-latency-response, multi-turn-conversation, summarization
Integrations: [object Object], [object Object], [object Object], [object Object]
Use Cases: [object Object], [object Object], [object Object], [object Object], [object Object]
API Available: Yes
Parameters: ~3.8B
Context Window: 128K
Modalities: text
Training Cutoff: 2024
Tags: small-language-model, on-device-ai, edge-computing, microsoft-research, efficient-inference, instruction-tuned, mobile-ai, resource-constrained, open-source, phi-3
Added: 2026-03-17
Completeness: 0.9%

Index Score

63.9

Adoption

Quality

Freshness

Citations

Engagement

Need help choosing the right model?

Get Expert Guidance

Explore the full AI ecosystem on Agents as a Service