Gemma 3n models
4 Gemma 3n models from Google on Hugging Face, from 5.4B to 8.4B parameters, published by Google in BF16, with a 32K-token context. The smallest official model, gemma-3n-E2B-it, needs about 12.2 GB of VRAM at its published precision; the cheapest live fit is RTX 5060 Ti at $0.173/hr.
Part of the Gemma series · Previous generation: Gemma 3 · Next generation: Gemma 4
Pick a size
One row per official Gemma 3n size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| gemma-3n-E2B-it | 5.4B | 12.2 GB | 6.1 GB | 3.0 GB | RTX 5060 Ti | $0.173/hr | 0.40 GB |
| gemma-3n-E4B-it | 7.8B | 17.5 GB | 8.8 GB | 4.4 GB | RTX A5000 | $0.176/hr | 0.46 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| gemma-3n-E2B-it | 5.4B | BF16 | 12.2 GB | RTX 5060 Ti | $0.173/hr |
| gemma-3n-E4B-it | 7.8B | BF16 | 17.5 GB | RTX A5000 | $0.176/hr |
Quantized versions (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| gemma-3n-E4B-it-MLX-bf16 | 7.8B | BF16 | 17.5 GB | RTX A5000 | $0.176/hr |
Fine-tunes and community models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| gemma-3n-E4B-it | 8.4B | BF16 | 18.7 GB | RTX A5000 | $0.176/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.