Microsoft

Phi-4 reasoning mini 3.8B

reasoning

3,8B

Parameters

2,3 Go

Q4_K_M file

≥ 3,8 Go

Recommended VRAM

131 072

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 3,8 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.

Technical sheet

Published: 2025-04-29
Architecture: 32 layers · 8 KV heads · dimension 128
Attention: Standard: every layer keeps the whole context in memory.
Context cache (f16): ≈ 125 MB per 1,000 tokens · 4,0 Go for 32,768 tokens
GGUF file: bartowski/microsoft_Phi-4-mini-reasoning-GGUF · microsoft_Phi-4-mini-reasoning-Q4_K_M.gguf Download (2,3 Go)
Official repo: microsoft/Phi-4-mini-reasoning

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