← Back to Models
Googletransformer
Gemma 2 27B
27B parameters • 16.4GB VRAM (Q4 estimate) • 8,192 context
Estimate · Q4_K_M · 4k context · batch 1. For dense 7B–70B this sits ~5–8% above the Q4_K_M GGUF file. Not peak runtime VRAM and not a measured bench.
Specifications
Parameters
27B
VRAM (Q4 est.)
16.4 GB
VRAM (FP16)
54 GB
Context Window
8,192
Architecture
transformer
License
Gemma License
Finding cloud alternatives...
Run Gemma 2 27B on RX 7900 XT
~16.4GB VRAM needed at Q4. RX 7900 XT has 20GB — buy hardware or rent cloud.
We may earn a commission from cloud and hardware partners at no extra cost to you.
Find the cheapest GPU that can run Gemma 2 27B
Compatibility Lab — check every GPU × quantization combination