← Back to Models
Googletransformer
Gemma 4 E4B
8B total / 4.5B effective · load estimate uses total • 4.9GB VRAM (Q4 estimate) • 128,000 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
8B total / 4.5B effective · load estimate uses total
VRAM (Q4 est.)
4.9 GB
VRAM (FP16)
16 GB
Context Window
128,000
Architecture
transformer
License
Apache-2.0
Finding cloud alternatives...
Run Gemma 4 E4B on Tesla K20c
~4.9GB VRAM needed at Q4. Tesla K20c has 5GB — 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 E4B
Compatibility Lab — check every GPU × quantization combination