LLM Opex

Models

gemma-2-9b: GPU memory and hosting cost

Open weights · 9.24 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 46.2 GB of GPU memory at fp32, the precision it ships in.

CloudCheapest instance that fitsGPUsAn hourA month, around the clock
DeepInfraa100.1x1 × A100 80 GB$1.49$1,088
Crusoel40s.1x1 × L40S 48 GB$1.50$1,095
Nebiusgpu-l40s-a.1gpu-8vcpu-32gb1 × L40S 48 GB$1.55$1,130
HF Endpointsaws.nvidia-l40s.x11 × L40S 48 GB$1.80$1,314
AWSg6e.xlarge1 × L40S 48 GB$1.86$1,359
Alibaba Cloudecs.gn8is.2xlarge1 × L20 48 GB$2.26$1,648
Core42h100.1x1 × H100 80 GB$2.50$1,825
AzureStandard_NC72ds_xl_RTXPRO6000BSE_v61 × RTX PRO 6000 48 GB$2.83$2,066
IBM watsonxdeploy-on-demand.1xL40S1 × L40S 48 GB$4.43$3,234
Google Cloudg4-standard-481 × RTX PRO 6000 96 GB$4.50$3,285
Fireworks AIh100.1x1 × H100 80 GB$8.00$5,840
OCIBM.GPU.L40S.44 × L40S 48 GB$14.00$10,220
Together AIhgx-h100.8gpu8 × H100 80 GB$31.92$23,302

More from Google

Similar size, open weights

List prices collected 21 November 2026, refreshed every three hours. No negotiated rates or taxes.