Gemma

Topic	Replies	Views	Activity
Gemma 4 - Launch Announcement announcement introducing Gemma 4 — our most intelligent open models to date. Purpose-built for advanced reasoning and agentic workflows, Gemma 4 delivers an unprecedented level of intelligence-per-parameter. This breakthrough builds …	1	318	April 5, 2026
About the Gemma Forum announcement	4	3009	December 11, 2025
Show & Tell: Backplaned — A self-hosted multi-agent orchestration platform (works great with Gemma 4) models	0	13	April 12, 2026
Disable thinking for Gemma 4 thinking	0	77	April 9, 2026
Regression: Gemma-4-E4B-it cannot initialize on mobile (LiteRT Engine Error) github	5	249	April 9, 2026
GEMMA API. Important question - TOS, does this violate the rules? api	1	81	April 7, 2026
Will it be possible to use fully local/offline Gemini Live AI models on devices in the future? ai	0	129	April 5, 2026
How to get access to SignGemma? ai , language-translator	5	2874	April 3, 2026
Gemma3n-2b Mobile Development models , research	3	518	March 26, 2026
Gemma3 1B Mobile Development models , showcase	8	965	March 8, 2026
A structural observer for epistemic drift model	4	90	March 2, 2026
Gemma 3 support for packed sequence training with FlashAttention 2? models	2	277	February 26, 2026
URGENT: Cloud Run L4 GPU Quota Blocked for MedGemma 4B Deployment api , models , medgemma	1	67	February 24, 2026
Ambiguous pronoun reference, Inconsistent verb tenses & Homophone confusion prompt	2	55	February 19, 2026
MedGemma-27B on GCP: Is there a way to deploy "pay-per-token" or serverless (without long spin-up times)? gcp	1	120	February 16, 2026
SignGemma Release date documentation	2	511	February 14, 2026
Experimenting with running TranslateGemma 4B locally in Zotero github , language-translator	5	167	February 12, 2026
Query on mixed-language outputs in the google/gemma-3n-4b-it model models	5	428	January 30, 2026
EmbeddingGemma indexing is extremely slow when used for knowledge indexing in Dify (Docker setup) gemini-embedding	3	156	January 29, 2026
Gemma 3n Input Token Count Limit api , rate-limits	1	113	January 23, 2026
Gemma 3n stable, when audio file support? ai-studio , gemma-3	2	295	January 20, 2026
Is EmbeddingGemma guaranteed to run fully offline without any external network communication? gemma	1	90	January 18, 2026
Inquiry regarding the evaluation setup for FunctionGemma on BFCL benchmark help-request , function-calling	2	107	January 9, 2026
SignGemma Availability ai-studio , research	1	1016	December 14, 2025
Inquiry Regarding QAT Version of Gemma-27B Model models	1	374	December 9, 2025
Experimental anti-hallucinatory api , models , gemini	1	286	November 26, 2025
Example audios to gemma 3n 4b model as a few shot example for low resource languages gpu , medgemma	1	277	November 19, 2025
Is the vLLM-compatible model Gemma‑3n‑E4B‑IT supported for audio concurrency? audio , gemma-3	1	345	November 6, 2025
[BUG] Gemma 3 27b and other Gemma models are not supported for image/file uploads gemma-3	6	1265	October 9, 2025
I use VPN for all my work to protect myself but can't connect to the Gemma AI and other Services ai , google-cloud	1	1012	September 17, 2025

Gemma 4 - Launch Announcement

announcement

introducing Gemma 4 — our most intelligent open models to date. Purpose-built for advanced reasoning and agentic workflows, Gemma 4 delivers an unprecedented level of intelligence-per-parameter. This breakthrough builds …