Apakah input saya muat?
Gabungkan teks, gambar, video, dan audio dalam batas bersama 8.192 token.
Diperbarui untuk rilis 6 Oktober 2026
Ketahui kebutuhan konfigurasi EmbeddingGemma 2 sebelum membangunnya.
Untuk pengembang RAG dan pencarian multimodal: hitung batas input, penyimpanan vektor, dan dimensi tepat dalam satu menit.
✓ Tanpa kunci API
✓ Tanpa unggah file
✓ Berjalan di browser
✓ Data model resmi
768dnative output
8,192shared input tokens
740Mfull model parameters
4input modalities
NILAI DALAM BAHASA SEDERHANA
Jawab tiga pertanyaan mahal sebelum deployment.
Masukkan beban kerja sekali dan dapatkan titik awal praktis tanpa membaca banyak dokumen atau membuat skrip uji.
Berapa penyimpanan yang dibutuhkan?
Perkirakan vektor, metadata, indeks, replika, dan biaya bulanan.
Konfigurasi mana untuk memulai?
Bandingkan 128–768 dimensi dan salin konfigurasi Python yang sesuai.
01 / INPUT BUDGET
Apakah input multimodal ini muat?
Teks, gambar, video, dan audio berbagi batas 8.192 token.
Fits comfortably81%
6,620 / 8,192 tokens
02 / VECTOR STORAGE
Seberapa besar indeksnya?
Perkirakan vektor, metadata, dan overhead indeks.
Estimated indexed footprint
952 MiB
Raw vectors488 MiB
Metadata244 MiB
Index overhead220 MiB
Monthly storage$0.25
03 / DIMENSION DECISION
Vektor lebih kecil tidak selalu lebih baik.
Bandingkan kualitas resmi dan penghematan dengan pengujian sendiri.
04 / MODEL FOOTPRINT
Muat hanya encoder yang dibutuhkan.
Parameters loaded270M
Approx. raw BF16 weights515 MiB
Weight estimate excludes framework, activations, caches and runtime overhead.
05 / METHODOLOGY
Lihat isi perhitungan secara jelas.
Semua asumsi terlihat dan dapat diubah.
One shared context
Text tokens + images × visual tokens + sampled video frames × visual tokens + audio seconds × 25.
Total ≤ 8,192 tokens
Storage before provider fees
Vector values and metadata are calculated first, then multiplied by index overhead and replica count.
(vectors + metadata) × (1 + overhead) × replicas
Weights, not total VRAM
The model estimate uses selected encoder parameters × two bytes for BF16 weights. Runtime memory is additional.
parameters × 2 bytes
Last source check: October 12, 2026. Model behavior and provider pricing can change. Verify against the linked official documentation before production use.
06 / SAFE STARTER
Salin konfigurasi yang sesuai.
Kode mengikuti dimensi dan modalitas pilihan.
07 / PRACTICAL ANSWERS
Sebelum membuat indeks.
Which EmbeddingGemma 2 dimension should I use?
Start with 256d for storage-sensitive text retrieval, and 512d or 768d when code or multimodal recall matters more. Treat 128d as a text-first shortlist candidate, not a universal default. Benchmark on representative queries before re-indexing production data.
Why must truncated vectors be normalized?
Slicing a normalized 768d vector changes its length. Re-normalizing keeps cosine similarity meaningful. Google specifically recommends using truncate_dim together with normalize_embeddings=True.
Does this calculator call an API or upload my data?
No. All calculations run in your browser. The tool does not ask for files, prompts, credentials or an API key.
Is the model footprint estimate the same as required VRAM?
No. It estimates raw BF16 weights only. Real VRAM or RAM usage also includes the framework, activations, temporary tensors, caches, media processing and operating-system overhead.
Is the storage result my final vector database bill?
No. It is a planning estimate for vectors, metadata, index overhead and replicas. A provider may also charge for compute, operations, backups, network transfer and minimum capacity.
Can I mix text, images, video and audio in one input?
Yes. EmbeddingGemma 2 maps these modalities into one shared vector space, but all media and text inside one input share the same 8,192-token budget.
SOURCE DISCIPLINE