Google

Gemma 3n E2B

small machines

5,4B

Parameters

2,6 Go

Q4_K_M file

≥ 4,1 Go

Recommended VRAM

32 768

Max context

Standard llama-bench run (prompt 512 / generation 128 tokens), model fully in VRAM. Click a card for details. Electricity cost at the default price (0,25 €/kWh).

Card · Q4_K_MVRAMGenerationPromptVRAM usedPower€ elec. / M tokPrice
RTX 4070 Ti12 Go163 tok/s8 2222,5 Go106 W0,05 €/M tok—

Not measured on these cards yet — click for an estimate:

Technical sheet

Published
2025-06-12
Architecture
30 layers · 2 KV heads · dimension 256
Attention
Sliding window: 6 of 30 layers keep the whole context, the others only the last 512 tokens — a much lighter cache.
Context cache (f16)
≈ 12 MB per 1,000 tokens · 0,4 Go for 32,768 tokens
GGUF file
bartowski/google_gemma-3n-E2B-it-GGUF · google_gemma-3n-E2B-it-Q4_K_M.gguf Download (2,6 Go)

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