Microsoft

Phi-3.5 mini 3.8B

3,8B

Parameters

2,2 Go

Q4_K_M file

≥ 3,7 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 3,7 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.

Technical sheet

Published
2024-08-16
Architecture
32 layers · 32 KV heads · dimension 96
Attention
Standard: every layer keeps the whole context in memory.
Context cache (f16)
≈ 375 MB per 1,000 tokens · 12,0 Go for 32,768 tokens
GGUF file
bartowski/Phi-3.5-mini-instruct-GGUF · Phi-3.5-mini-instruct-Q4_K_M.gguf Download (2,2 Go)

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