Model · Phi · Reviewed June 2026

standardMIT14B paramsOpen weights

Phi-3 Medium 128K Instruct

Microsoft · Phi

14B parameter open-weight model. 14B with 128K context. Q4 fits in 12 GB VRAM. Strong reasoning for size. Context-heavy RAG tasks benefit from the long window.

Editorial review

Reviewed byOpenSourcesAI EditorialLast updatedJune 2026SourcesHuggingFace model card (microsoft/Phi-3-medium-128k-instruct), official docs, OpenSourcesAI editorial review.

VRAM figures are empirical estimates. Actual usage varies by runtime, context length, and system configuration. Verify on your specific hardware before production use.

Related models

Phi-4 MiniBuilders testing small local models on laptops, CPUs, and constrained hardware.Phi-4Small language model reasoning and assistant workflows

Ready to run this model locally?

Find a compatible interface in our Local AI Tools directory →