← Back to Models
Googletransformer
Gemma 4 31B
30.7B parameters • 18.7GB VRAM (Q4 estimate) • 256,000 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
30.7B
VRAM (Q4 est.)
18.7 GB
VRAM (FP16)
61.4 GB
Context Window
256,000
Architecture
transformer
License
Apache-2.0
Finding cloud alternatives...
Run Gemma 4 31B on RTX 4000 Ada
~18.7GB VRAM needed at Q4. RTX 4000 Ada 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 4 31B
Compatibility Lab — check every GPU × quantization combination