Gemma 4 E4B IT
Gemma 4 E4B is the larger edge model in Google DeepMind's Gemma 4 family: 4.5B effective parameters (8B including embeddings), native text and image input, a 128K-token context window, configurable thinking and function calling, released as open weights under Apache 2.0.
Model
Gemma 4 E4B is a 42-layer dense transformer designed for laptops and mobile devices. Like E2B it uses Per-Layer Embeddings, so of its 8B total parameters only about 4.5B are effective in compute, which is what the E denotes. A ~150M-parameter vision encoder processes images at variable aspect ratios and resolutions with a configurable visual token budget. Hybrid local sliding-window and global attention with Proportional RoPE supports a 128K-token context, and the model offers a switchable thinking mode, native function calling and a system role. It scores 69.4% on MMLU Pro and 52.0% on LiveCodeBench v6.
This is the instruction-tuned variant, released as open weights under the Apache 2.0 license. Google recommends sampling at temperature 1.0, top-p 0.95 and top-k 64, placing images before the text in a prompt, and enabling thinking by prefixing the system prompt with the think control token. Full details are in Google's announcement and the model card.
Dedicated Endpoint
DocsA Dedicated Endpoint is your own deployment of Gemma 4 E4B IT, on an inference stack that Modal tunes and autoscales. Bring fine-tuned weights if you have them. Compute is billed by the second, and only while it runs.
modal endpoint create --model google/gemma-4-E4B-it