What GPU do I need to run google/gemma-2-27b?

27.2B parameters, published in F32. View on Hugging FaceGated

27.2B
Parameters
F32
Native precision
Gemma2ForCausalLM
Architecture
text-generation
Pipeline

gemma-2-27b is published by google on Hugging Face, with 10,920 downloads and 211 likes to date. It's a Gemma2ForCausalLM model built for text-generation, published natively in F32, and gated: you'll need to accept the model's terms on Hugging Face before downloading weights.

VRAM required & cheapest live GPU fit

Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP32101.4 GB121.7 GBAMD MI300X1$2.63/hr
cheaper alt.V1008$0.880/hr
FP8 (quantized)25.4 GB30.4 GBRTX 5000 Ada1$0.539/hr
cheaper alt.RTX 5060 Ti2$0.361/hr
INT4 (quantized)12.7 GB15.2 GBRTX A40001$0.167/hr

A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.

INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.

Cheapest way to run gemma-2-27b at its published (F32) precision: 1× AMD MI300X, at $2.63/hr per GPU ($2.63/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.

gemma-2-27b: KV cache by context length

The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.

Sliding-window attention: windowed layers stop growing at the window, the full-attention layers keep growing. Cached per token: 376,832 bytes at 16-bit while the context is inside the window.

ContextKV cache, one sequence
4K1.4 GB
8K (model maximum)2.2 GB

Computed from the layer, head and window counts in the model's own configuration (unsloth/gemma-2-27b), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.

gemma-2-27b: common questions

Can gemma-2-27b run on a single GPU?

Yes, but not on a desktop card. At FP32 it needs 121.7 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 192.0 GB AMD MI300X at $2.63/hr.

Do I need approval to download gemma-2-27b?

Yes. google gates this repository on Hugging Face, so you have to accept its terms with a signed-in account before the weights will download. It does not change the 121.7 GB the model needs once you have them.

Can gemma-2-27b run in 16-bit instead of FP32?

Yes. Its published weights are FP32, 101.4 GB, or 121.7 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 50.7 GB, or 60.9 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.

What is the least VRAM gemma-2-27b can run in?

15.2 GB, at INT4 (quantized), which fits a 16 GB card, against 121.7 GB at FP32. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.

Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.

More Gemma 2 models

All 11 Gemma 2 models: VRAM and GPU requirements

Lineage

Quantized and fine-tuned versions

Alternatives at this size

Other models for text-generation within about a third of gemma-2-27b's 27.2B parameters, from other model lines.

More on gemma-2-27b

Related reading: AMD MI300X pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.

Your own GPU cloud accounts

One console for the GPU clouds you already rent from. Your keys stay on your machine.

$20 a month, flat

Connect your accounts

One console for the GPU clouds you already use.

Connect your accounts for $20 a month, flat. Your provider bills the GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.