EmbeddingGemma 2 is modular: load only 270M for text-only on phones and laptops
tomaarsen · x · 2026-10-07
EmbeddingGemma 2's 740M footprint is modular: text 270M, vision 170M, audio 300M. Unused encoders can be disabled via configkwargs — text-only loads 270M, text+images 440M, text+audio 570M. The design targets phones and laptops by loading only the encoders you need.
More from Infra
- CostGraph becomes a drop-in InfraCost replacement for comparing GPU prices from L40 to A100 — saheedniyi_02 · 2026-10-07
- Oki Home launches a $1,799 Memory Computer running a 27B model locally with up to 16TB Memchip storage — Scobleizer · 2026-10-07
- Phonon-2 hits 606x real-time on a MacBook Air: one hour of speech in 6 seconds — julianweisser · 2026-10-07
- Show HN: openTPU claims AI can now design its own inference hardware — fsbonetto · 2026-10-07
- Mistral Large 4 trained on just 4,000 Grace Blackwell GPUs vs 100,000 for Astra — steipete · 2026-10-07
- SpaceX shows off Starmind plan: 1M-satellite Starlink clusters with 10 Tb/s links for AI compute — XFreeze · 2026-10-07