Gemma 4 31B

Gemma 4 31B is an open-weight language model from Google DeepMind, released on April 2, 2026.

Developer: Google DeepMind
Released: April 2, 2026
Total parameters: 30.7B
Architecture: Dense
Context window: 256K
Input: Text, image
License: Apache 2.0
Commercial use: Yes
Official weights, GB: 62.5 GB
Hugging Face repository: huggingface.co
Checked on: September 29, 2026

Gemma 4 31B is a dense model with 30.7B parameters. Google DeepMind lists a context window of 256K tokens. The model accepts text and image input. The weights are released under Apache 2.0, which allows commercial use. The official weights on Hugging Face take about 62.5 GB in BF16. Running the model needs at least that much memory across GPUs and system RAM, plus room for the context cache; quantized versions need less.

Total parameters, billions: 30.7B
Context window, tokens: 256K
License type: Apache 2.0
License conditions: Apache 2.0: keep the license and notices; no limits on field of use or number of users. Gemma 4 is the first Gemma generation under Apache 2.0; earlier versions used the Gemma Terms of Use.
Weights precision: BF16
Official quantized or alternative versions: google/gemma-4-31B-it-qat-q4_0-gguf; google/gemma-4-31B-it-qat-q4_0-unquantized; google/gemma-4-31B-it-qat-w4a16-ct
License text: ai.google.dev
Sources: Page URL
Hugging Face model card https://huggingface.co/google/gemma-4-31B-it/raw/main/README.md
blog.google announcement https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
opensource.googleblog.com announcement https://opensource.googleblog.com/2026/03/gemma-4-expanding-the-gemmaverse-with-apache-20.html
Hugging Face API https://huggingface.co/api/models?author=google&search=gemma-4
Hugging Face weights index https://huggingface.co/google/gemma-4-31B-it/raw/main/model.safetensors.index.json

Page	URL
Hugging Face model card	https://huggingface.co/google/gemma-4-31B-it/raw/main/README.md
blog.google announcement	https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
opensource.googleblog.com announcement	https://opensource.googleblog.com/2026/03/gemma-4-expanding-the-gemmaverse-with-apache-20.html
Hugging Face API	https://huggingface.co/api/models?author=google&search=gemma-4
Hugging Face weights index	https://huggingface.co/google/gemma-4-31B-it/raw/main/model.safetensors.index.json

Questions

What license does Gemma 4 31B use?

The weights are released under Apache 2.0, which allows commercial use. Gemma 4 is the first Gemma generation under Apache 2.0; earlier versions used the Gemma Terms of Use.

Can I use Gemma 4 31B commercially?

Yes. Keep the license and notices; there are no limits on field of use or number of users.

How much memory does Gemma 4 31B need?

The official Gemma 4 31B weights take about 62.5 GB (BF16). Google also publishes quantization-aware 4-bit versions, including a GGUF build, which need less. The memory calculator checks which setups fit.

How many parameters does Gemma 4 31B have?

Gemma 4 31B is a dense model with 30.7B parameters, the largest dense model in the Gemma 4 family listed here, with a context window of 256K tokens.

Sources

Every figure comes from the developer’s model card, license text and official announcements, and from the model’s Hugging Face repository metadata. Each model page lists its sources and the date they were checked; the register is rechecked every week.