Google · Official-source model record
gemma 4 E2B it
gemma · Version google/gemma-4-E2B-it
Publisher-sourced inventory. Specifications come from official documentation and model cards. “Not documented” means we have no verified value. This inventory is separate from our editorial reviews.
Coverage & sources ↗Current catalog answers
What to know about gemma 4 E2B it
AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026.
Which gemma 4 E2B it does this page describe?
gemma 4 E2B it is a model record from Google in the gemma family. Source
The recorded model identifier or checkpoint is google/gemma-4-E2B-it. Use that exact identifier when checking documentation or a provider listing. Source
How can you access gemma 4 E2B it?
The catalog documents Open weights access for gemma 4 E2B it. Source
As of the catalog check, this version was listed as available. Source
Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement.
What are gemma 4 E2B it's context and output limits?
The documented context window is 128,000 tokens. Source
A separate maximum-output value is not established in this record. The context or input figure should not be used as an output allowance.
Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity.
What dates are documented for gemma 4 E2B it?
Training-data cutoff: January 2025. Source This describes the reported data boundary, not the day training finished. The source labels this “Pre-training dataset cutoff.”
Retrieval or web tools can supply newer information at run time. That does not change the model's recorded training or knowledge dates, and this record does not establish that a particular endpoint includes those tools.
What can gemma 4 E2B it receive and generate?
Documented inputs: text, image, video, and audio. Source
Documented outputs: text. Source
Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation.
What license is recorded for gemma 4 E2B it?
The recorded license label is Apache-2.0. Source
Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service.
What is documented about the gemma 4 E2B it checkpoint?
This evidence refers to google/gemma-4-E2B-it at recorded revision 3e22461f65e89153144f8adb70e3b8c2cc9845a7, checked October 23, 2026. Repository metadata
Safetensors metadata records 5,123,178,051 stored parameters. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. Repository metadata
Recorded architecture class: Gemma4ForConditionalGeneration. Repository metadata
Repository task tag: any-to-any. A task tag identifies a distribution category; it does not measure performance on that task. Repository metadata
Listed library: transformers. Check that library's version and model support before loading the weights. Repository metadata
Repository access gate: false. This records the repository's gate setting when checked; licensing and use terms still apply. Repository metadata
What the configuration file says
The pinned config.json section text_config contains these values. Pinned configuration
max_position_embeddings- 131,072
sliding_window- 512
torch_dtype- bfloat16
num_attention_heads- 8
num_key_value_heads- 1
num_hidden_layers- 35
hidden_size- 1,536
Configuration values describe the checkpoint and its implementation. In particular, max_position_embeddings, sliding_window and rope_scaling do not independently establish an API context limit, tested usable length or hardware requirement. Runtime, quantization, cache, batch size and input length affect deployment behavior.
Read the retrieved model card for setup and qualifications. Model card
Keep the exact version in view
Other gemma models from Google.
These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses.
gemma 1.1 2b it
Open weights
gemma 1.1 7b it
Open weights
gemma 2 27b
Open weights
gemma 2 27b it
Open weights
gemma 2 2b
Open weights
gemma 2 2b it
Open weights
The documented record
Specifications, with their sources.
A missing value remains unknown. Input limits, output limits and the total context window are separate measurements.
- Publisher
- GoogleSource ↗
- Family
- gemmaSource ↗
- Version
- google/gemma-4-E2B-itSource ↗
- Availability
- AvailableSource ↗
- Access
- Open weightsSource ↗
- Inputs
- Text · Image · Video · AudioSource ↗
- Outputs
- TextSource ↗
- Context window
- 128,000 tokensSource ↗
- Maximum input
- Not documented
- Maximum output
- Not documented
- Knowledge cutoff
- Not documented
- Training-data cutoff
- Jan 2025Pre-training dataset cutoff · month precisionSource ↗
- Training completed
- Not documented
- Release date
- Not documented
- License
- Apache-2.0Source ↗
- Input price / 1M tokens
- Not documented
- Output price / 1M tokens
- Not documented
Read this with the numbers.
Official Google-published checkpoint. Base/pretrained and instruction-tuned variants remain distinct; platform and quantized packaging copies are excluded. Hosted API availability not inferred. K token limits reproduce vendor rounded units as decimal thousands; no exact integer precision is implied. Publisher repository evidence (2026-10-23): Publisher task label: any-to-any. Published architecture metadata: Gemma4ForConditionalGeneration. Repository library label: transformers. Published safetensors metadata counts 5,123,178,051 stored parameters; this is not an active-parameter count for mixture-of-experts models. Published text_config configuration: max_position_embeddings=131072; sliding_window=512; dtype=bfloat16; 35 hidden layers. Checkpoint configuration is not a verified hosted serving limit; context and output limits remain separate documented fields.
Model identifiers and aliases 0
No additional identifier has been verified.
Follow the evidence
Official sources.
- model_card_4 ↗ai.google.dev
- gemma 4 E2B it official reference ↗huggingface.co
- gemma 4 E2B it: official publisher repository metadata ↗huggingface.co
- gemma 4 E2B it: publisher model card at revision 3e22461f65e8 ↗huggingface.co
- gemma 4 E2B it: published checkpoint configuration at revision 3e22461f65e8 ↗huggingface.co