Gemma0.27B params33k contextpopular

Gemma 3 270M locally

Gemma 3 270M is an open-weight LLM from the Gemma family with 0.27B parameters. Main use: chat, RAG and general assistance. Detected minimum hardware: GTX 1650 (4 GB).

Technical facts
Parameters0.27B
Max context33k
Q4_K_M0.2 GB
Q5_K_M0.2 GB
Q80.3 GB
FP160.6 GB
FamilyGemma
Last sync2026-05-12

Available quantizations

Q4_K_M
0.2GB

Acceptable. Good compromise when VRAM is limited.

Q5_K_M
0.2GB

Good quality. Sweet spot for size and precision.

Q8
0.3GB

Near-FP16 quality. Comfortable for production.

FP16
0.6GB

Reference precision. Maximum quality, doubled VRAM.

Compatible GPUs

GPUs that can run Gemma 3 270M on a single card, ranked by VRAM headroom.

Recommended multi-GPU rigs

For Gemma 3 270M at higher quantization or with more context, a multi-GPU rig gives more headroom.

Recommended rig

2× GTX 1650

Gemma 3 270M with Ubuntu, vLLM, Open WebUI and the model already downloaded.

Configure

VRAM estimates: parameters x bits/8 plus margin. Real performance varies by engine, context length and batch size.
sync: 2026-05-12