Microsoft

Phi-4 reasoning 14B plus

reasoning

14,7B

Parameters

8,4 Go

Q4_K_M file

≥ 9,9 Go

Recommended VRAM

32 768

Max context

Not measured yet

No card has run the TokenBench protocol on this model yet. The current protocol covers a selection of models; benchmarking any catalog model from the app is coming soon.

Measure my card →

Which cards should it fit on?

Cards on the site whose video memory covers the recommended 9,9 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.

Technical sheet

Published: 2025-04-17
Architecture: 40 layers · 10 KV heads · dimension 128
Attention: Standard: every layer keeps the whole context in memory.
Context cache (f16): ≈ 195 MB per 1,000 tokens · 6,3 Go for 32,768 tokens
GGUF file: bartowski/microsoft_Phi-4-reasoning-plus-GGUF · microsoft_Phi-4-reasoning-plus-Q4_K_M.gguf Download (8,4 Go)
Official repo: microsoft/Phi-4-reasoning-plus

Public Hugging Face data (official config.json, GGUF repo). The context cache only counts full-attention layers.