@meta
  v: 1
  route: /model/gemma-4-e4b
  generated: 2026-06-10T09:23:25.253Z

@intent
  purpose:    Show what hardware can run Gemma 4 E4B.
  audience:   ai-engineer, self-hoster, model-evaluator
  capability: inspect_model_specs, find_compatible_gpus, compare_similar_models, open_huggingface

@state
  slug: gemma-4-e4b
  name: Gemma 4 E4B
  hf_repo: google/gemma-4-E4B-it
  params_b: 4
  active_params_b: ~
  family: Google
  type: dense
  context_k: 128
  fp16_gb: 8
  summary: "Google's April 2026 small Gemma. Multimodal-ready, 128K context."
  smallest_fitting_gpu_q4: rtx-3070
  smallest_fitting_gpu_fp16: rtx-3060

@actions
  - id: open_huggingface
    method: GET
    href: https://huggingface.co/google/gemma-4-E4B-it
  - id: view_compatible_gpus
    method: GET
    href: /model/gemma-4-e4b
  - id: compare_similar
    method: GET
    href: /model/phi-4-mini
  - id: view_calculator
    method: GET
    href: /#calculator

@context
  > Google's April 2026 small Gemma. Multimodal-ready, 128K context.

@nav
  self:      /model/gemma-4-e4b
  parents:   [/]
  peers:     [/model/phi-4-mini, /model/llama-3-2-3b, /model/llama-3-2-1b, /model/qwen-2-5-7b]
  drilldown: /the-math