gemma-3-270m-it: GPU memory and hosting cost
Open weights · 0.27 billion parameters · licence gemma
No cloud sells this model per token: to use it you run it yourself, on GPU instances you rent.
Run it yourself
It needs 0.7 GB of GPU memory at bf16, the precision it ships in.
| Cloud | Cheapest instance that fits | GPUs | An hour | A month, around the clock |
|---|---|---|---|---|
| Azure | Standard_NV6ads_A10_v5 | 1 × A10 4 GB | $0.454 | $331 |
| AWS | g4dn.xlarge | 1 × T4 16 GB | $0.526 | $384 |
| Google Cloud | g2-standard-4 | 1 × L4 24 GB | $0.7068 | $516 |
| Alibaba Cloud | ecs.gn6i-c4g1.xlarge | 1 × T4 16 GB | $1.12 | $816 |
More from Google
- Gemini 2.5 Flash
- Gemini 2.5 Flash Lite
- Gemini 2.5 Pro
- gemma-4-26B-A4B-it
- gemma-4-31b-it
- gemma-3-1b-it (google)
Similar size, open weights
- Qwen2.5-0.5B-Instruct
- Qwen2-0.5B-Instruct
- pythia-410m
- h2o-danube3-500m-chat
- Falcon-H1-0.5B-Base
- TIPO-500M-ft
List prices collected 5 October 2026, refreshed every three hours. No negotiated rates or taxes.