Rent a GPU

Gemma 4 26B-A4B hardware requirements

25.8B parameters (3.8B active, mixture of experts). Needs about 16.5 GB at Q4_K_M with 8K context.

Parameters26B3.8B active (MoE)
Q4_K_M · 8K16.5 GBthe usual download
FP16 · 8K52.5 GBfull precision
Runs well on18/51GPUs and Macs we track

Memory needed at each quantization

Weights, KV cache and runtime overhead, at 8K and 32K tokens of context.

QuantQuality8K context32K context
FP16Full quality52.5 GB52.7 GB
Q8_0Near-lossless28.3 GB28.6 GB
Q6_KExcellent22 GB22.3 GB
Q5_K_MVery good19.2 GB19.5 GB
Q4_K_MGood, most popular16.5 GB16.8 GB
Q3_K_MNoticeably degraded13.5 GB13.8 GB
Q2_KHeavily degraded10.6 GB10.8 GB

Run it with Ollama

Downloads Q4_K_M by default.

ollama run gemma4:26b

Model card

google/gemma-4-26B-A4B-it on Hugging Face: licence, prompt format and GGUF builds.

Run it in the cloud

Run Gemma 4 26B-A4B on a rented GPU today.

It needs about 16.5 GB at Q4_K_M: a rented RTX 3090 / RTX 4090 runs it for about $0.18 to $0.89 an hour.

RunPodRent a GPU on RunPodVast.aiRent a GPU on Vast.ai

Every GPU and Mac checked

Sorted by memory. Bars show how much of each card Gemma 4 26B-A4B fills at the best quant that fits.

18 Runs well

NameMemory usedBest quantSpeed

26 Fits with heavy quantization

NameMemory usedBest quantSpeed

7 Too big

NameMemory usedBest quantSpeed

Other Gemma models