LLM Reference
NVIDIA NIM

Gemma 3n 4B (free) on NVIDIA NIM

Gemma 3 · Google DeepMind

ServerlessOpen Weights

Last refreshed 2026-05-22. Next refresh: weekly.

Why use Gemma 3n 4B (free) on NVIDIA NIM?

NVIDIA NIM offers Gemma 3n 4B (free) with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.

Compare Gemma 3n 4B (free) across 3 providers to find the best fit for your use case
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: google/gemma-3n-e4b-it
Model ID
google/gemma-3n-e4b-it

Request example

Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID google/gemma-3n-e4b-it.

Gotchas

  • Use provider model ID "google/gemma-3n-e4b-it", not the LLMReference slug "gemma-3n-e4b-it".

Compare Gemma 3n 4B (free) Across Providers

ProviderInput (per 1M)Output (per 1M)
NVIDIA NIM
Together AI$0.02$0.04
OpenRouter$0.06$0.12

Capabilities

Structured Outputs

About Gemma 3n 4B (free)

Google: Gemma 3n 4B (free) available via OpenRouter. Pricing: $null/1M input, $null/1M output.

FAQ

What is the context window for Gemma 3n 4B (free) on NVIDIA NIM?

Gemma 3n 4B (free) supports a 8k token context window on NVIDIA NIM.

How does NVIDIA NIM compare to other Gemma 3n 4B (free) providers?

Gemma 3n 4B (free) is available from 3 providers. The cheapest input pricing is $0.02/1M tokens from Together AI.

What API model ID do I use for Gemma 3n 4B (free) on NVIDIA NIM?

Use the model ID google/gemma-3n-e4b-it when calling NVIDIA NIM's API.

Who created Gemma 3n 4B (free)?

Gemma 3n 4B (free) was created by Google DeepMind as part of the Gemma 3 model family.

Is Gemma 3n 4B (free) open source?

Gemma 3n 4B (free) has open weights under Gemma according to the seed data, but that does not necessarily mean an OSI-approved open-source license.

Get Started

Model Specs

Released2025-04-03
Parameters8B (4B effective active)
Context8k
ArchitectureDecoder Only
Knowledge cutoff2024-06