Gemma 3 27B IT

Checkpoint identity

Official identifier

google/gemma-3-27b-itGoogle Gemma 3 27B IT model card (external source) · Google official Gemma PyTorch configuration (external source) · Gemma Terms of Use (external source)

Architecture

Multimodal transformer; text decoder with vision encoderGoogle Gemma 3 27B IT model card (external source) · Google official Gemma PyTorch configuration (external source) · Gemma Terms of Use (external source)

Total parameters

27 billionPublished rounded counts; total stored weights determine the preliminary footprint, including all MoE experts.Google Gemma 3 27B IT model card (external source) · Google official Gemma PyTorch configuration (external source) · Gemma Terms of Use (external source)

Active parameters

Not verified for this recordActive parameters are a compute-related count, not the model's full stored weight count.Google Gemma 3 27B IT model card (external source) · Google official Gemma PyTorch configuration (external source) · Gemma Terms of Use (external source)

Modalities

text-input, image-input, text-outputGoogle Gemma 3 27B IT model card (external source) · Google official Gemma PyTorch configuration (external source) · Gemma Terms of Use (external source)

Context

131,072 tokensNative configuration where directly verified. Extensions, advertised K-labels and configuration differences are preserved in the notes below.Google Gemma 3 27B IT model card (external source) · Google official Gemma PyTorch configuration (external source) · Gemma Terms of Use (external source)

Release date

Exact release date not independently established in the reviewed artifactsGoogle Gemma 3 27B IT model card (external source) · Google official Gemma PyTorch configuration (external source) · Gemma Terms of Use (external source)

Download access

Gated: publisher terms / access acceptanceGoogle Gemma 3 27B IT model card (external source) · Google official Gemma PyTorch configuration (external source) · Gemma Terms of Use (external source)

License

Gemma Terms of UseCustom Gemma terms govern weights, derivatives and hosted services. They require passing on use restrictions, providing terms to recipients and applicable notices, with a prohibited-use policy. Model access is gated by acceptance. Google’s separately licensed code is not the weight license.Google Gemma 3 27B IT model card (external source) · Google official Gemma PyTorch configuration (external source) · Gemma Terms of Use (external source)

Theoretical weight-memory footprint

Using the publisher's approximately 27 billion total parameters at 16 bits per parameter gives 54 GB (50.3 GiB) of nominal weights.

This estimate excludes KV cache, activations, quantization metadata, non-weight buffers and serving overhead. It is not a tested GPU fit. MoE routing activates only part of the network per token while the complete expert weights still need storage.

Quantization

The selected checkpoint has BF16 weights. Quantization choices must preserve the vision path and be validated for the exact backend.

Serving considerations

• 27B is a rounded checkpoint size. An independently documented activated-parameter count is not supplied and is left null.
• Google's official 27B v3 config specifies 131,072 positions; the card describes 128K total input context and an 8,192-token output context. Image tokens consume context and processing resources.
• Google's reference PyTorch repository is archived; use it as configuration evidence, not a promise of maintained deployment support. Aguasto has not accepted terms, evaluated or deployed this checkpoint.

Framework documentation

These are third-party documentation starting points. Support depends on the exact checkpoint, runtime version and hardware.