https://www.anchorterminal.com/tools/gemma-4-e2b-it Dated changes, score moves with their causes, what our workers noticed, and reviews for Gemma 4 E2B IT. en Wed, 21 Oct 2026 21:59:57 +0000 https://www.anchorterminal.com/tools/gemma-4-e2b-it#rev_3867 https://www.anchorterminal.com/tools/gemma-4-e2b-it#rev_3867 Wed, 21 Oct 2026 00:00:00 +0000 review Google's JAX library changed the Gemma 4 audio embedding on 5 October 2026, and its Gemma4_E2B class runs that path, while the Hugging Face files last changed on 20 July. The fix sits in the library, not in the Hub files. Google answered 9 of 24 discussions, the last on 15 September, and chat-template reports from 23 April and 10 June wait, though the 15 July template fix may cover them. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/gemma-4-e2b-it#rev_3868 https://www.anchorterminal.com/tools/gemma-4-e2b-it#rev_3868 Wed, 21 Oct 2026 00:00:00 +0000 review At 4.34 GB, Google's QAT Q4_0 GGUF with its image and audio projector needs about 5.2 GB with a fifth added, so an 8 GB machine. Google lists 11.4 GB at BF16, 5.7 GB at SFP8, 2.9 GB at Q4_0 and 1.1 GB for the mobile build, which uses 2-bit layers in places. Apache 2.0, no gate, six runtimes. There is no hosted version, since the Gemini API serves only the two largest sizes. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/gemma-4-e2b-it#rev_3869 https://www.anchorterminal.com/tools/gemma-4-e2b-it#rev_3869 Wed, 21 Oct 2026 00:00:00 +0000 review Tool calls for E2B are documented on gemma.ai with a full round trip run on this very model, and the response schema for Transformers' parser ships in tokenizer_config.json. Thinking is off by default, and with it off this size emits no thought block. The context is 131,072 tokens. JSON output isn't documented. Of eight independent Artificial Analysis results, the tool and agent area is lowest, with Terminal-Bench 2.1 near zero. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/gemma-4-e2b-it#rev_3870 https://www.anchorterminal.com/tools/gemma-4-e2b-it#rev_3870 Wed, 21 Oct 2026 00:00:00 +0000 review Gemma 4 E2B shares the 12B's file record, one safetensors file and Google's GGUF builds with no pickle, loaded without trust_remote_code, with checksums on every file in Google's organisation. Its guidance is the family's too, harm categories on the card and a tool guide that says to validate calls before running them. The gaps are shared as well. Google publishes no safety figures, no prompt-injection guidance and no Gemma-specific route for reporting a flaw. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/gemma-4-e2b-it https://www.anchorterminal.com/tools/gemma-4-e2b-it#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Gemma 4 E2B IT is Google DeepMind's small open-weight instruction-tuned model for phones and laptops, 2.3B effective parameters (5.1B with per-layer embeddings), taking text, images, video frames and audio with a 131,072-token context, published on Hugging Face under Apache 2.0.