Google

Gemma 2 2B

2,6B

Parameters

1,6 Go

Q4_K_M file

≥ 3,1 Go

Recommended VRAM

8 192

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 3,1 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.

Technical sheet

Published
2024-07-16
Architecture
26 layers · 4 KV heads · dimension 256
Attention
Sliding window: 13 of 26 layers keep the whole context, the others only the last 4096 tokens — a much lighter cache.
Context cache (f16)
≈ 51 MB per 1,000 tokens · 1,6 Go for 32,768 tokens
GGUF file
bartowski/gemma-2-2b-it-GGUF · gemma-2-2b-it-Q4_K_M.gguf Download (1,6 Go)

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