gemma-4-E2B-it
Official · BF16 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
Gemma · Edge · Gemma 4 Edge
Gemma 4 E2B IT: Specs, GPU requirements, hosting & deployment
Gemma 4 E2B IT is a current Edge release in the Gemma family, certified from its immutable official source revision.
Total parameters5.1B
Active parameters2.0B
Context window131,072 tokens
Release statusCurrent · Current
ArchitectureGemma4ForConditionalGeneration
ModalitiesText, Image, Audio
LicenseApache License 2.0
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2026-03-02
Architecture, strengths and use cases
Gemma 4 E2B IT is an official self-hostable Google release in the Gemma Edge track. It uses Gemma4ForConditionalGeneration, carries 5.1B / 2B MoE, supports a verified context window of 131,072 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 4 E2B IT uses Gemma4ForConditionalGeneration with 5.1B / 2B MoE. The stored architecture profile records 35 layers, hidden width 1536, 8 attention heads and a 131,072 token context ceiling where the official configuration publishes those fields.
Verified Gemma4ForConditionalGeneration architecture
131,072 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 memory9.78 GB
KV cache0.27 GB
Runtime overhead6.53 GB
Total with safety margin20.57 GB
Recommended best value
1× NVIDIA A100 SXM 80GB
80 GB total VRAM · nvlink
59.43 GB headroom · Available
USD 915 / monthLowest-cost viable
1× NVIDIA L4 24GB
24 GB total VRAM · pcie
3.43 GB headroom · Available
USD 250 / monthHighest performance
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
120.43 GB headroom · Limited capacity
USD 2,345 / monthLicense and self-hosting considerations
The full 5.1B 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 4 E2B IT is published under Apache License 2.0. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
Alternatives and sibling variants
Gemma 4 E4B IT, Gemma 3n E2B
Release timeline
google/gemma/gemma-4-e2b-it
Source details
Source revision: be66af288433ffc4907653977bf433bb99dfb24c6512e620243c8d4545168f95
Frequently asked questions
How much VRAM does Gemma 4 E2B IT 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 4 E2B IT?
Certified upstream runtime evidence is available for transformers.
Can Gemma 4 E2B IT be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official Apache License 2.0 terms for the final obligations.
Official references
Last verified: 2026-08-26