How much VRAM does embeddinggemma-300m need?

Q4_0 is exactly 277,852,192 bytes (0.26 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

google · text

embeddinggemma-300m

google/embeddinggemma-300m

embeddinggemma-300m at Q4_0 is exactly 277,852,192 bytes (0.26 GiB / 0.28 GB) — an effective 7.339 bits per weight, not the nominal 4.

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

Parameters

303M

Architecture

gemma-embedding

24 layers

Context

2,048

native (config.json)

License

—

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_0	0.26 GiB	277,852,192	7.339	314	unsloth
IQ4_XS	0.28 GiB	303,472,192	8.016	316	cstr
Q4_K	0.28 GiB	305,978,944	8.082	—	cstr
Q5_K	0.30 GiB	318,660,160	8.417	—	cstr
Q8_0	0.31 GiB	328,577,056	8.679	314	unsloth
Q8_0	0.31 GiB	333,590,944	8.812	316	ggml-org
Q8_0	0.33 GiB	356,703,808	9.422	—	cstr
BF16	0.57 GiB	612,429,792	16.177	—	unsloth
F32	1.13 GiB	1,217,982,432	32.172	—	unsloth

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 Llama-3.2-1B-Instruct vs Wan2.1-T2V-1.3B vs LFM2.5-1.2B-Instruct vs gemma-3-1b-it vs Qwen3-0.6B vs Qwen2.5-1.5B-Instruct All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_0 at roughly 0.16 GiB. The real file is 0.26 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from mirror:unsloth/embeddinggemma-300m

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 need?: Q4_0 is exactly 277,852,192 bytes (0.26 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 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.