Phi also joined the ranks of the reasoning models. The "plus" variant uses GRPO on top of an SFT model. We found the model surprisingly capable in our testing considering both the size and the reputation of the Phi series as benchmark-maxers.
Specs
Params14B
LicenseMIT
Tags
modelsmodels/llmsmodels/llms/reasoningartifacts/10
RAM score
—
Hugging Face Downloads
13.6K
last 30d
404.8K
all time
HF Likes
344
Relative Adoption Metric contextualizes downloads against the model's size bucket.
VAIL Fingerprint
02a7:0334:04cb:0749:0ab9:125e:1a6d:6028
Explore other models with behavioral similarity to Phi-4-reasoning-plus.
Related Models
