How much VRAM does gemma-4-E2B-it-qat-q4_0-unquantized need?

Q4_0 is exactly 3,349,515,424 bytes (3.12 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is gemma-4-E2B-it-qat-q4_0-unquantized's KV cache?

0.25 GiB at 32K context with an f16 cache, computed per layer from the model's architecture — most of its layers use sliding-window attention, so a flat formula overstates this substantially. Quantizing the cache to q8_0 roughly halves it.

google · text

gemma-4-E2B-it-qat-q4_0-unquantized

google/gemma-4-E2B-it-qat-q4_0-unquantized

gemma-4-E2B-it-qat-q4_0-unquantized at Q4_0 is exactly 3,349,515,424 bytes (3.12 GiB / 3.35 GB) — an effective 5.250 bits per weight, not the nominal 4. Its KV cache at 32K is 0.25 GiB, not the 1.09 GiB a flat formula predicts.

From the file· summed from 1 file(s)From the file· KV per layer

Parameters

5.1B

Architecture

gemma4

35 layers

Context

131,072

native (config.json)

License

apache-2.0

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_0	3.12 GiB	3,349,515,424	5.250	541	lmstudio-community
Q4_K	3.18 GiB	3,416,118,240	5.354	—	huihui-ai
BF162 shards	8.80 GiB	9,443,738,048	14.801	—	huihui-ai

KV cache by context

computed per layer — this model uses sliding-window attention

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.05 GiB	0.14 GiB	2.50×	7 / 28 / 0
8,192	0.08 GiB	0.27 GiB	3.33×	7 / 28 / 0
16,384	0.14 GiB	0.55 GiB	4.00×	7 / 28 / 0
32,768	0.25 GiB	1.09 GiB	4.44×	7 / 28 / 0
65,536	0.46 GiB	2.19 GiB	4.71×	7 / 28 / 0
131,072	0.90 GiB	4.38 GiB	4.85×	7 / 28 / 0

28 of 35 layers cache only a 512-token window rather than the full context, on a period of . Figures assume the default configuration; --swa-full disables the saving entirely.

Compare with

same modality, comparable size

vs Qwen3-Coder-30B-A3B-Instruct vs gemma-4-12B-it-qat-q4_0-unquantized vs gemma-4-E4B-it vs Qwen3-30B-A3B-Thinking-2507 vs Qwen3-4B vs Qwen3-8B 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 2.67 GiB. The real file is 3.12 GiB, because a quantization is a mixture and some tensors are always kept at higher precision. The larger discrepancy is the cache: a flat formula gives 1.09 GiB at 32K context where the real figure is 0.25 GiB, because most of this model's layers cache a fixed window rather than the whole context.

Architecture

from config.json

Layers

Attention heads

KV heads

Head dim

256

Hidden size

1536

Vocab

262,144

Sliding window

512

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does gemma-4-E2B-it-qat-q4_0-unquantized need?: Q4_0 is exactly 3,349,515,424 bytes (3.12 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is gemma-4-E2B-it-qat-q4_0-unquantized's KV cache?: 0.25 GiB at 32K context with an f16 cache, computed per layer. Quantizing the cache to q8_0 roughly halves it, which is often the difference between a context length fitting and not.
Which quantization of gemma-4-E2B-it-qat-q4_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.