Google Gemma 4 E4B: an Apache-2.0 any-to-any model for on-device AI
goyalshaliniuk · x · 2026-11-04
Entry #2 in a thread on 7 small language models: Google's Gemma 4 E4B, a compact model designed for mobile devices and laptops. It accepts text, image, audio, and video inputs (any-to-any pipeline), offers a 128K-token context window, ships under Apache 2.0 with 8B BF16 parameters, and targets on-device AI and multimodal applications.
Related event: 7 Small Language Models to Watch in 2026-27: A Scene-Based Roundup(9 posts)→
More from Models
- Hobbyist rewrites Qwen 0.6B weights with 39.8M tokens, no gradients, in 3h12m — Altruistic_Heat_9531 · 2026-11-04
- Same leak, reshared: ChatGPT's five family plan prices spotted again — heyshrutimishra · 2026-11-04
- KOL visits StepFun's Shanghai office, hints a powerful new model is coming — teortaxesTex · 2026-11-04
- Fable 5.5 delayed as Anthropic reportedly bets OpenAI's Astra 6.2 won't beat it — haider1 · 2026-11-04
- ByteDance open-sources Axion 1.0-35B agent foundation model with full reproducible recipe — pmttyji · 2026-11-04
- Community asks Moonshot when Kimi K3.1 model weights will drop — bgmshana · 2026-11-04