gemma-3n-E2B
Official · BF16 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
Gemma · Edge · Gemma 3n
Gemma 3n E2B: Specs, GPU requirements, hosting & deployment
Gemma 3n E2B is a recent Edge release in the Gemma family, certified from its immutable official source revision.
Total parameters6.0B
Active parameters2.0B
Context window32,768 tokens
Release statusRecent · Recent
ArchitectureGemma3nForConditionalGeneration
ModalitiesText, Image, Audio, Video
LicenseGemma Terms of Use
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed With Conditions
Release date2025-06-12
Architecture, strengths and use cases
Gemma 3n E2B is an official self-hostable Google release in the Gemma Edge track. It uses Gemma3nForConditionalGeneration, carries 6B / 2B MoE, supports a verified context window of 32,768 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
Gemma 3n E2B uses Gemma3nForConditionalGeneration with 6B / 2B MoE. The stored architecture profile records 64 layers, hidden width 8192, 64 attention heads and a 32,768 token context ceiling where the official configuration publishes those fields.
Verified Gemma3nForConditionalGeneration architecture
32,768 token certified context
Official BF16, Unknown checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Vision-language analysis
Audio understanding
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed transformers runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Estimated weight memory11.51 GB
KV cache2 GB
Runtime overhead7.15 GB
Total with safety margin25.62 GB
Recommended best value
1× NVIDIA A100 SXM 80GB
80 GB total VRAM · nvlink
54.38 GB headroom · Available
USD 915 / monthLowest-cost viable
2× NVIDIA L4 24GB
48 GB total VRAM · pcie
22.38 GB headroom · Available
USD 500 / monthHighest performance
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
115.38 GB headroom · Limited capacity
USD 2,345 / monthLicense and self-hosting considerations
The full 6B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
Gemma 3n E2B is published under Gemma Terms of Use. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed With Conditions. Commercial use is conditional. Review the linked official terms before deployment.
Alternatives and sibling variants
Gemma 4 E4B IT, Gemma 4 E2B IT
Release timeline
google/gemma/gemma-3n-e2b
Source details
Source revision: 1cbda28222e5fb69d6cf53e29594dd640db7c46ebfcb906f79b8f84644a07020
Frequently asked questions
How much VRAM does Gemma 3n E2B require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Which runtimes support Gemma 3n E2B?
Certified upstream runtime evidence is available for transformers.
Can Gemma 3n E2B be used commercially?
The stored commercial classification is Commercial Use Allowed With Conditions. Consult the official Gemma Terms of Use terms for the final obligations.
Official references
Last verified: 2026-08-26