#sparsemodel
Live, measured metrics for the hashtag #sparsemodel from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #sparsemodel
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 · fosstodon.org (Mastodon public tags API) · fetched 2026-07-27 10:03 UTC0 uses by 0 unique accounts across the window. Real per-day counts, not estimates. Newest bar is today so far.
Related hashtags
measured · fosstodon.org (Mastodon public search API) · fetched 2026-07-27 10:03 UTCLive pulse
measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-27 10:03 UTCEverything below is measured over the latest 2 public posts (spanning ~1181 hours).
Posting hours (UTC)
Languages: English (2)
Avg boosts / post: 0
Used together with
Top of the latest posts
Alex Cheema (@alexocheema) arcee_ai 모델이 Apple Silicon RDMA 클러스터와 exolabs에서 잘 동작한다고 소개했다. 이 모델은 398B 규모에 활성 파라미터는 13B로 매우 희소해 Apple Silicon에 적합하며, 전체 모델은 약 800GB라 4대의 256GB Mac Studio가 필요하다. 6-bit로도 구동 가능하다고 언급했다. https://x.com/alexocheema/s
Rohan Paul (@rohanpaul_ai) 1조 파라미터급 Kimi K2.5 모델을 RTX 3060 12GB 한 장과 768GB의 중고 Intel Optane 메모리로 초당 4토큰 이상 속도로 구동했다는 사례. 희소(sparse) 모델과 대용량 저비용 메모리 계층을 결합해 초대형 모델 추론을 하드웨어 제약 아래서 가능하게 만든 점이 핵심이다. https://x.com/rohanpaul_ai/status/2058431032
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/sparsemodel