How much VRAM does embeddinggemma-300m-qat-q8_0-unquantized need?

Q8_0 is exactly 328,577,056 bytes (0.31 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

google · embedding

embeddinggemma-300m-qat-q8_0-unquantized

google/embeddinggemma-300m-qat-q8_0-unquantized

embeddinggemma-300m-qat-q8_0-unquantized at Q8_0 is exactly 328,577,056 bytes (0.31 GiB / 0.33 GB) — an effective 8.679 bits per weight, not the nominal 8.

From the file· summed from 1 file(s)From the file· KV from mirror (mirror:unsloth/embeddinggemma-300m-qat-q8_0-unquantized)

Parameters

303M

Architecture

gemma-embedding

24 layers

Context

2,048

native (config.json)

License

gemma

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q8_0	0.31 GiB	328,577,056	8.679	314	ggml-org

No KV cache

architectural, not a gap in our data

This architecture allocates no KV cache. Encoder and embedding models process their input in one pass rather than generating token by token, so there is nothing to carry forward between steps and memory does not grow with context. Its footprint is the weights plus a working buffer, and that is the whole story.

Compare with

same modality, comparable size

vs jina-embeddings-v5-text-small vs KaLM-embedding-multilingual-mini-instruct-v2.5 vs nomic-embed-text-v1.5 vs jina-embeddings-v5-text-nano vs nomic-embed-text-v2-moe vs bge-m3 All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q8_0 at roughly 0.16 GiB. The real file is 0.31 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from mirror:unsloth/embeddinggemma-300m-qat-q8_0-unquantized

Layers

Attention heads

KV heads

Head dim

256

Hidden size

768

Vocab

262,144

Sliding window

512

SWA period

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does embeddinggemma-300m-qat-q8_0-unquantized need?: Q8_0 is exactly 328,577,056 bytes (0.31 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of embeddinggemma-300m-qat-q8_0-unquantized should I use?: Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.