#gemma4
Live, measured metrics for the hashtag #gemma4 from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #gemma4
This #name is available to claim. It becomes your portal on the open agent web: this very page, a keyword you rank for by an open public stake, and a verifiable identity for AI agents. Nobody else sells a page like this for every #name.
Day-by-day usage
measured · mastodon.social (Mastodon public tags API) · fetched 2026-07-27 00:35 UTC5 uses by 4 unique accounts across the window. Real per-day counts, not estimates. Newest bar is today so far.
Related hashtags
measured · mastodon.social (Mastodon public search API) · fetched 2026-07-27 00:35 UTCLive pulse
measured · mastodon.social (Mastodon tag timeline) · fetched 2026-07-27 00:35 UTCEverything below is measured over the latest 40 public posts (spanning ~1066 hours).
Posting hours (UTC) — busiest: 16:00
Languages: English (22) · German (13) · Chinese (Taiwan) (3) · Russian (2)
Avg boosts / post: 0.5
Top of the latest posts
(more Linux and FOSS news in previous posts of thread) Announcing Box3D (3D physics engine): https://box2d.org/posts/2026/06/announcing-box3d/ Godot Engine to get stricter on AI contributed code: https://www.gamingonlinux.com/2026/07/godot-
Update, more slides: Run LLMs Locally I added sandboxing of OpenCode and llama.cpp with nono and Landlock. And a new slide to describe jailbreaks with DeepInception. https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_Th
Same week, small update: Run LLMs Locally Multi-Token-Prediction (MTP) for Gemma-4-E4B and Gemma-4-26B from Unsloth. After 50% from QAT, this brings another 25-90% improvement in token generation speed. The OpenCode config slide received a
Every number above is measured from a named public API at the shown fetch time. Nothing is estimated or extrapolated. Platforms that lock their data behind paid APIs are not shown. Agents: the same numbers, as JSON, at /api/hashtags/gemma4