← Back to Models
Googletransformer
Gemma 3n E2B
6B total / 2B effective · load estimate uses total • 3.6GB VRAM (Q4 estimate) • 32,000 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
6B total / 2B effective · load estimate uses total
VRAM (Q4 est.)
3.6 GB
VRAM (FP16)
12 GB
Context Window
32,000
Architecture
transformer
License
Gemma
Finding cloud alternatives...
Run Gemma 3n E2B on Radeon RX 6500 XT
~3.6GB VRAM needed at Q4. Radeon RX 6500 XT has 4GB — 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 3n E2B
Compatibility Lab — check every GPU × quantization combination