Google

Gemma 4 E4B

vision

8B

Parameters

5,0 Go

Q4_K_M file

≥ 6,5 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 6,5 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.

Technical sheet

Published
2026-03-02
Architecture
42 layers · 2 KV heads · dimension 256
Attention
Sliding window: 7 of 42 layers keep the whole context, the others only the last 512 tokens — a much lighter cache.
Context cache (f16)
≈ 14 MB per 1,000 tokens · 0,4 Go for 32,768 tokens
GGUF file
bartowski/google_gemma-4-E4B-it-GGUF · google_gemma-4-E4B-it-Q4_K_M.gguf Download (5,0 Go)

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