gemma-4-31B-it
Official · BF16 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
Gemma · General · Gemma 4
Gemma 4 31B IT: Specs, GPU requirements, hosting & deployment
Gemma 4 31B IT is a current General release in the Gemma family, certified from its immutable official source revision.
Total parameters31.3B
Active parametersDense model
Context window262,144 tokens
Release statusCurrent · Current
ArchitectureGemma4ForConditionalGeneration
ModalitiesText, Image
LicenseApache License 2.0
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2026-03-11
Architecture, strengths and use cases
Gemma 4 31B IT is an official self-hostable Google release in the Gemma General track. It uses Gemma4ForConditionalGeneration, carries 31.3B, supports a verified context window of 262,144 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 31B IT uses Gemma4ForConditionalGeneration with 31.3B. The stored architecture profile records 60 layers, hidden width 5376, 32 attention heads and a 262,144 token context ceiling where the official configuration publishes those fields.
Verified Gemma4ForConditionalGeneration architecture
262,144 token certified context
Official BF16, Unknown checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Vision-language analysis
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 memory60.05 GB
KV cache7.5 GB
Runtime overhead16.88 GB
Total with safety margin104.69 GB
Recommended best value
2× NVIDIA A100 SXM 80GB
160 GB total VRAM · nvlink
55.31 GB headroom · Available
USD 1,830 / monthLowest-cost viable
5× NVIDIA L4 24GB
120 GB total VRAM · pcie
15.31 GB headroom · Available
USD 1,250 / monthHighest performance
2× NVIDIA A100 SXM 80GB
160 GB total VRAM · nvlink
55.31 GB headroom · Available
USD 1,830 / monthLicense and self-hosting considerations
The full 31.3B 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 31B 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 26B-A4B IT, Gemma 4 12B IT, Gemma 3 27B IT
Release timeline
google/gemma/gemma-4-31b-it
Source details
Source revision: 1dca95601edc592cb830650ae3d2dc3773c2679aaba5de14fb673215f3a5e4d9
Frequently asked questions
How much VRAM does Gemma 4 31B 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 31B IT?
Certified upstream runtime evidence is available for transformers.
Can Gemma 4 31B 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