Back to Phi 3
Microsoft's 3.8B Phi-3 Mini instruct model with 4K context — same strong reasoning as the 128k variant in a smaller memory footprint.
4K tokensFree / Open weightsTransformerMIT
No benchmark scores available yet for this model.
Microsoft's 3.8B Phi-3 Mini instruct model with 4K context — same strong reasoning as the 128k variant in a smaller memory footprint.
No benchmark scores available yet for this model.