by Google DeepMind

Gemma 2B It.

text open weights edge 2B params 8K ctx

Smallest GPU

1× Nvidia Titan V

Smallest GPU to run it See all quantisations →

1× Nvidia Titan V.

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
Together AI	hosted inference	—	—	Launch ↗

FAQ

Frequently asked.

How do I run Gemma 2B It?

Gemma 2B It 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 2B It?

Gemma 2B It is available via Together AI. Each access option lists its own pricing (per million tokens or hourly hosting).

How much does it cost to run Gemma 2B It?

Self-hosting cost depends on the GPU you rent and the throughput you need. See the Run It Yourself tab for GPU configurations and hourly cost estimates.

Is Gemma 2B It open-source or proprietary?

Gemma 2B It is open-weight under the license. You can download and self-host it.

Run it yourself

Cheapest hardware per quantisation.

Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr refreshed hourly from each provider's API.

Quantisation	Cheapest GPU config	Total VRAM	Live $/hr	tokens/sec
FP16 FP16 — half precision (default)	1× Nvidia Nvidia P102-100	5 GB	—	—	Compare →
FP8 FP8 — 8-bit float (Hopper / Blackwell)	1× Nvidia Nvidia Titan V	3 GB	—	—	Compare →
INT4 INT4 — 4-bit integer (~4× VRAM saving)	1× Nvidia Nvidia Titan V	3 GB	—	—	Compare →

Just need an API?

Skip the GPU rental and call a hosted endpoint instead. See access providers on the Overview tab →

Gemma 2B It.

1× Nvidia Titan V.

Cheapest hosted endpoints.

Frequently asked.

Cheapest hardware per quantisation.

How much it can remember.

What it can do.