← Back to Models
Gemma 3N
Gemma 3N is a variant of the Gemma 3 model, optimized for enhanced performance and efficiency. Note these are not chat models.
gemma-3n-e2b
5B parameters
Base
Pull this model
Use the following command with the HoML CLI:
homl pull gemma-3n:e2bResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| BF16 | 10 GB | 10 GB |
gemma-3n-e2b-it
5B parameters
Instruction-Tuned
Pull this model
Use the following command with the HoML CLI:
homl pull gemma-3n:e2b-itResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| BF16 | 10 GB | 10 GB |
gemma-3n-e4b
10B parameters
Base
Pull this model
Use the following command with the HoML CLI:
homl pull gemma-3n:e4bResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| BF16 | 20 GB | 20 GB |
gemma-3n-e4b-it
10B parameters
Instruction-Tuned
Pull this model
Use the following command with the HoML CLI:
homl pull gemma-3n:e4b-itResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| BF16 | 20 GB | 20 GB |