How much VRAM does gemma4-26B-it need?

Q4_K_M is exactly 16,796,015,488 bytes (15.64 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

google · vision language

gemma4-26B-it

google/gemma4-26B-it

gemma4-26B-it at Q4_K_M is exactly 16,796,015,488 bytes (15.64 GiB / 16.80 GB) — an effective 5.325 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)

Parameters

25.2B

Architecture

gemma4

Context

—

native (config.json)

License

apache-2.0

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_K_M	15.64 GiB	16,796,015,488	5.325	—	Jackrong
Q5_K_M	17.82 GiB	19,132,889,984	6.066	—	Jackrong
Q6_K	21.08 GiB	22,638,398,848	7.177	—	Jackrong
Q8_0	25.02 GiB	26,859,858,816	8.516	—	Jackrong

Compare with

same modality, comparable size

vs Qwen3.6-35B-A3B vs Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP vs Qwen3.5-9B vs gemma-4-26B-A4B-it vs gemma-4-12B-it vs Qwen3.5-4B All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 13.22 GiB. The real file is 15.64 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

Architecture unavailable — this repository is gated and no ungated mirror was found. Exact file sizes above are still authoritative; only the KV math needs the config.

Questions people ask

How much VRAM does gemma4-26B-it need?: Q4_K_M is exactly 16,796,015,488 bytes (15.64 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of gemma4-26B-it 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.