by Google DeepMind

Gemma 2 27B.

text open weights laptop+ 27B params 8K ctx
Cheapest input
$0.65/M
on OpenRouter
Cheapest output
$0.65/M
on OpenRouter
Smallest GPU
1× NVIDIA Quadro RTX 6000
$0.14/hr

Gemma 2 27B is Google's open-weights English text model under the Gemma license, instruction-tuned here, for chat, summarization and question answering.

Smallest GPU to run it See all quantisations →

1× NVIDIA Quadro RTX 6000 · $0.14/hr.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $0.65 $0.65 Launch ↗
Together AI hosted inference $0.8 $0.8 Launch ↗
Sources

Official references.

Family

Variants in the Gemma family.

FAQ

Frequently asked.

How do I run Gemma 2 27B?
Gemma 2 27B is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Gemma 2 27B?
Gemma 2 27B is available via Together AI, OpenRouter, Ollama. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Gemma 2 27B?
API pricing starts at $0.65/M input tokens and $0.65/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Gemma 2 27B open-source or proprietary?
Gemma 2 27B is open-weight under the Gemma Terms of Use license. You can download and self-host it.