Gemma 3

gemma-3-4b-it

Google DeepMind · open-restricted gemma

Parameters (B)4.3
Architecturedense
Layers / KV heads / head dim34 / 4 / 256
Context window131072
Modalitiesin: text, image; out: text
GGUFavailable
Commercial useyes

Minimum hardware (estimate)

At Q4_K_M and 8k context, total working set ≈ 4.3 GiB. On a machine with 64 GiB system RAM and no discrete GPU: CPU-only, slow. Limiting factor: No GPU VRAM; fits in system RAM but inference will be CPU-bound.

Open in fit advisor

Scores

No Tier A comparable scores ingested yet for this model.

Provenance

HF: google/gemma-3-4b-it · snapshot 2026-08-10