{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/gemma-4/","md":"https://postcutoff.com/m/gemma-4/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"gemma-4","name":"Gemma 4","org":"Google DeepMind","family":"Gemma","released":"2026-04-02","status":"current","type":"llm","modality_in":["text","image","audio","video"],"modality_out":["text"],"open_weights":true,"model_license":"apache-2.0","context_window":262144,"max_output":null,"knowledge_cutoff":null,"pricing":{"input":0.09,"output":0.34,"unit":"per 1M tokens, OpenRouter price for google/gemma-4-31b-it (26B-A4B: $0.09 / $0.30; free variants exist). Weights free to download","source":"https://openrouter.ai/google/gemma-4-31b-it"},"price_line":"$0.09 in, $0.34 out per 1M tokens","access":[{"provider":"Hugging Face","model_id":"google/gemma-4-31B-it","url":"https://huggingface.co/google/gemma-4-31B-it"},{"provider":"Hugging Face","model_id":"google/gemma-4-26B-A4B-it","url":"https://huggingface.co/google/gemma-4-26B-A4B-it"},{"provider":"Hugging Face","model_id":"google/gemma-4-12B-it","url":"https://huggingface.co/google/gemma-4-12B-it"},{"provider":"Hugging Face","model_id":"google/gemma-4-E4B-it","url":"https://huggingface.co/google/gemma-4-E4B-it"},{"provider":"Hugging Face","model_id":"google/gemma-4-E2B-it","url":"https://huggingface.co/google/gemma-4-E2B-it"},{"provider":"OpenRouter","model_id":"google/gemma-4-31b-it"},{"provider":"OpenRouter","model_id":"google/gemma-4-26b-a4b-it"},{"provider":"Google docs","docs":"https://ai.google.dev/gemma/docs/core"}],"capabilities":[{"name":"First Apache-2.0 Gemma","detail":"First Gemma generation under the permissive Apache 2.0 license instead of Google's custom Gemma terms.","first":false,"discovered":"launch","source":"https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/"},{"name":"Intelligence per parameter","detail":"31B dense ranked #3 and 26B A4B MoE #6 among open models on Arena at launch.","first":false,"discovered":"launch","source":"https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/"},{"name":"On-device agentic models","detail":"E2B/E4B edge models with native audio+vision, function calling and structured JSON, running offline on phones/Raspberry Pi/Jetson.","first":false,"discovered":"launch","source":"https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/"},{"name":"Encoder-free unified 12B","detail":"Gemma 4 12B, added later, is a unified encoder-free multimodal model with native audio.","first":false,"discovered":"later","source":"https://ai.google.dev/gemma/docs/core"}],"entry":null,"notes":"Sizes E2B, E4B (128K context), 12B, 26B A4B MoE, 31B dense (256K context); base and -it variants plus QAT/GGUF quantized repos. 12B released later (HF repo 2026-05-23). Audio input on E2B/E4B/12B only. 140+ languages. pricing is third-party (OpenRouter), not Google.","verified":"2026-09-29","body_md":"Latest open-weights family from Google DeepMind (built from Gemini 3 research); run locally or self-host.\n\n```python\nfrom transformers import pipeline\npipe = pipeline(\"image-text-to-text\", model=\"google/gemma-4-E4B-it\")\nprint(pipe(text=[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Hello!\"}]}]))\n```\n\nSources: [Gemma docs](https://ai.google.dev/gemma/docs/core), [launch blog](https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/), [HF repo](https://huggingface.co/google/gemma-4-31B-it).","page_url":"https://postcutoff.com/m/gemma-4/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":1887,"you_url":"https://postcutoff.com/you/gemma-4/","briefings":null}