--- title: "Gemma 3 27B IT | Aguasto" description: "Research reference for Gemma 3 27B IT: official checkpoint, license and memory considerations. Documented in Aguasto Research; no Aguasto deployment or API availability is represented." canonical: "https://www.aguasto.com/models/gemma-3-27b-it" last-updated: "2026-10-12" --- # Gemma 3 27B IT | Aguasto Canonical HTML: [Gemma 3 27B IT](https://www.aguasto.com/models/gemma-3-27b-it) > Research reference for Gemma 3 27B IT: official checkpoint, license and memory considerations. Documented in Aguasto Research; no Aguasto deployment or API availability is represented. [Aguasto](https://www.aguasto.com/) [Model Index](https://www.aguasto.com/models) Gemma 3 27B IT [Resources](https://www.aguasto.com/resources) [GPU Library](https://www.aguasto.com/gpus) [Model Index](https://www.aguasto.com/models) [Inference Stack](https://www.aguasto.com/inference-stack) [Learn](https://www.aguasto.com/learn) [Insights](https://www.aguasto.com/insights) [Research](https://www.aguasto.com/research) [Engineering tools](https://www.aguasto.com/tools) Google DeepMind / Open-weight checkpoint reference ## Gemma 3 27B IT Documented in Aguasto Research. This checkpoint has not been evaluated or deployed by Aguasto and is not available through an Aguasto API. Original Aguasto conceptual illustration. Not manufacturer geometry, an operating Aguasto asset, or a measured benchmark. Aguasto Research documents third-party hardware, models and software. References do not represent Aguasto inventory, evaluated deployments or available inference services. ### Checkpoint identity Official identifier google/gemma-3-27b-it[Google Gemma 3 27B IT model card (external source)](https://huggingface.co/google/gemma-3-27b-it) · [Google official Gemma PyTorch configuration (external source)](https://github.com/google/gemma_pytorch/blob/main/gemma/config.py) · [Gemma Terms of Use (external source)](https://ai.google.dev/gemma/terms) Architecture Multimodal transformer; text decoder with vision encoder[Google Gemma 3 27B IT model card (external source)](https://huggingface.co/google/gemma-3-27b-it) · [Google official Gemma PyTorch configuration (external source)](https://github.com/google/gemma_pytorch/blob/main/gemma/config.py) · [Gemma Terms of Use (external source)](https://ai.google.dev/gemma/terms) Total parameters 27 billionPublished rounded counts; total stored weights determine the preliminary footprint, including all MoE experts.[Google Gemma 3 27B IT model card (external source)](https://huggingface.co/google/gemma-3-27b-it) · [Google official Gemma PyTorch configuration (external source)](https://github.com/google/gemma_pytorch/blob/main/gemma/config.py) · [Gemma Terms of Use (external source)](https://ai.google.dev/gemma/terms) Active parameters Not verified for this recordActive parameters are a compute-related count, not the model's full stored weight count.[Google Gemma 3 27B IT model card (external source)](https://huggingface.co/google/gemma-3-27b-it) · [Google official Gemma PyTorch configuration (external source)](https://github.com/google/gemma_pytorch/blob/main/gemma/config.py) · [Gemma Terms of Use (external source)](https://ai.google.dev/gemma/terms) Modalities text-input, image-input, text-output[Google Gemma 3 27B IT model card (external source)](https://huggingface.co/google/gemma-3-27b-it) · [Google official Gemma PyTorch configuration (external source)](https://github.com/google/gemma_pytorch/blob/main/gemma/config.py) · [Gemma Terms of Use (external source)](https://ai.google.dev/gemma/terms) Context 131,072 tokensNative configuration where directly verified. Extensions, advertised K-labels and configuration differences are preserved in the notes below.[Google Gemma 3 27B IT model card (external source)](https://huggingface.co/google/gemma-3-27b-it) · [Google official Gemma PyTorch configuration (external source)](https://github.com/google/gemma_pytorch/blob/main/gemma/config.py) · [Gemma Terms of Use (external source)](https://ai.google.dev/gemma/terms) Release date Exact release date not independently established in the reviewed artifacts[Google Gemma 3 27B IT model card (external source)](https://huggingface.co/google/gemma-3-27b-it) · [Google official Gemma PyTorch configuration (external source)](https://github.com/google/gemma_pytorch/blob/main/gemma/config.py) · [Gemma Terms of Use (external source)](https://ai.google.dev/gemma/terms) Download access Gated: publisher terms / access acceptance[Google Gemma 3 27B IT model card (external source)](https://huggingface.co/google/gemma-3-27b-it) · [Google official Gemma PyTorch configuration (external source)](https://github.com/google/gemma_pytorch/blob/main/gemma/config.py) · [Gemma Terms of Use (external source)](https://ai.google.dev/gemma/terms) License Gemma Terms of UseCustom Gemma terms govern weights, derivatives and hosted services. They require passing on use restrictions, providing terms to recipients and applicable notices, with a prohibited-use policy. Model access is gated by acceptance. Google’s separately licensed code is not the weight license.[Google Gemma 3 27B IT model card (external source)](https://huggingface.co/google/gemma-3-27b-it) · [Google official Gemma PyTorch configuration (external source)](https://github.com/google/gemma_pytorch/blob/main/gemma/config.py) · [Gemma Terms of Use (external source)](https://ai.google.dev/gemma/terms) ### Theoretical weight-memory footprint Using the publisher's approximately 27 billion total parameters at 16 bits per parameter gives **54 GB** (50.3 GiB) of nominal weights. weight GB = total parameters in billions × bits per weight / 8 This estimate excludes KV cache, activations, quantization metadata, non-weight buffers and serving overhead. It is not a tested GPU fit. MoE routing activates only part of the network per token while the complete expert weights still need storage. [Explore the memory estimator](https://www.aguasto.com/tools) #### Quantization The selected checkpoint has BF16 weights. Quantization choices must preserve the vision path and be validated for the exact backend. [Google Gemma 3 27B IT model card (external source)](https://huggingface.co/google/gemma-3-27b-it) · [Google official Gemma PyTorch configuration (external source)](https://github.com/google/gemma_pytorch/blob/main/gemma/config.py) · [Gemma Terms of Use (external source)](https://ai.google.dev/gemma/terms) ### Serving considerations - 27B is a rounded checkpoint size. An independently documented activated-parameter count is not supplied and is left null. - Google's official 27B v3 config specifies 131,072 positions; the card describes 128K total input context and an 8,192-token output context. Image tokens consume context and processing resources. - Google's reference PyTorch repository is archived; use it as configuration evidence, not a promise of maintained deployment support. Aguasto has not accepted terms, evaluated or deployed this checkpoint. [Google Gemma 3 27B IT model card (external source)](https://huggingface.co/google/gemma-3-27b-it) · [Google official Gemma PyTorch configuration (external source)](https://github.com/google/gemma_pytorch/blob/main/gemma/config.py) · [Gemma Terms of Use (external source)](https://ai.google.dev/gemma/terms) #### Framework documentation These are third-party documentation starting points. Support depends on the exact checkpoint, runtime version and hardware. ### Continue the research [vLLM](https://www.aguasto.com/inference-stack/vllm) [SGLang](https://www.aguasto.com/inference-stack/sglang) [Compare model references](https://www.aguasto.com/models/compare) [GPU specification library](https://www.aguasto.com/gpus) [Weights, cache and serving overhead](https://www.aguasto.com/learn/model-weights-and-runtime-memory) ### Sources & verification Reference revision 1 · Reviewed October 12, 2026. Manufacturer claims and documentation are attributed; Aguasto has not run the cited products in production. - [Google Gemma 3 27B IT model card ↗](https://huggingface.co/google/gemma-3-27b-it) 27B rounded checkpoint size; BF16 weights; text and image input / text output; 128K input and 8192 output context statements; gated terms acceptance; vLLM / SGLang references. Publication: date not stated in the reviewed source. Verified: 2026-10-12. - [Google official Gemma PyTorch configuration ↗](https://github.com/google/gemma_pytorch/blob/main/gemma/config.py) 27B v3 max\_position\_embeddings is 131072; text and vision configuration; repository archived status. Publication: date not stated in the reviewed source. Verified: 2026-10-12. - [Gemma Terms of Use ↗](https://ai.google.dev/gemma/terms) Gemma 3 is included in the terms appendix; hosted-service and derivative definitions; redistribution and prohibited-use conditions; different terms apply to Gemma 4. Last modified: 2026-04-01. Verified: 2026-10-12. ### Reference journey [Compare models ↗](https://www.aguasto.com/models/compare) [Estimate weights ↗](https://www.aguasto.com/tools) [Hardware references ↗](https://www.aguasto.com/gpus) [Aguasto inference strategy ↗](https://www.aguasto.com/ai-inference) [Sources & verification ↓](https://www.aguasto.com/models/gemma-3-27b-it#sources) Research reference · No available Aguasto service ## Company navigation - [Home](https://www.aguasto.com/) - [Infrastructure](https://www.aguasto.com/infrastructure) - [GPU Cloud](https://www.aguasto.com/gpu-cloud) - [AI Inference](https://www.aguasto.com/ai-inference) - [Development & Investment](https://www.aguasto.com/development) - [Company](https://www.aguasto.com/company) - [Contact](https://www.aguasto.com/contact) - [Privacy](https://www.aguasto.com/privacy) - [Resources](https://www.aguasto.com/resources) - [GPU Library](https://www.aguasto.com/gpus) - [Model Index](https://www.aguasto.com/models) - [Inference Stack](https://www.aguasto.com/inference-stack) - [Learn](https://www.aguasto.com/learn) - [Insights](https://www.aguasto.com/insights) - [Research](https://www.aguasto.com/research) - [Industry cases](https://www.aguasto.com/research/cases) - [Why Modular](https://www.aguasto.com/why-modular) - [Partners](https://www.aguasto.com/partners) - [GPU comparison](https://www.aguasto.com/gpus/compare) - [Model comparison](https://www.aguasto.com/models/compare) - [Engineering tools](https://www.aguasto.com/tools) - [Development friction](https://www.aguasto.com/research/hyperscale-development-friction) - [NVIDIA H100 SXM](https://www.aguasto.com/gpus/h100) - [NVIDIA H200 SXM](https://www.aguasto.com/gpus/h200) - [NVIDIA B200 SXM](https://www.aguasto.com/gpus/b200) - [NVIDIA B300](https://www.aguasto.com/gpus/b300) - [NVIDIA GB200 NVL72](https://www.aguasto.com/gpus/gb200-nvl72) - [NVIDIA GB300 NVL72](https://www.aguasto.com/gpus/gb300-nvl72) - [NVIDIA Vera Rubin NVL72](https://www.aguasto.com/gpus/vera-rubin-nvl72) - [AMD Instinct MI300X](https://www.aguasto.com/gpus/mi300x) - [AMD Instinct MI325X](https://www.aguasto.com/gpus/mi325x) - [AMD Instinct MI355X](https://www.aguasto.com/gpus/mi355x) - [AMD Instinct MI455X](https://www.aguasto.com/gpus/mi455x) - [AMD Helios](https://www.aguasto.com/gpus/helios) - [GLM-4.5](https://www.aguasto.com/models/glm-4-5) - [Qwen3-235B-A22B](https://www.aguasto.com/models/qwen3-235b-a22b) - [DeepSeek-R1](https://www.aguasto.com/models/deepseek-r1) - [Llama 3.3 70B Instruct](https://www.aguasto.com/models/llama-3-3-70b-instruct) - [Gemma 3 27B IT](https://www.aguasto.com/models/gemma-3-27b-it) - [gpt-oss-120b](https://www.aguasto.com/models/gpt-oss-120b) - [Kimi-K2-Instruct](https://www.aguasto.com/models/kimi-k2-instruct) - [vLLM](https://www.aguasto.com/inference-stack/vllm) - [SGLang](https://www.aguasto.com/inference-stack/sglang) - [TensorRT-LLM](https://www.aguasto.com/inference-stack/tensorrt-llm) - [NVIDIA Dynamo](https://www.aguasto.com/inference-stack/dynamo) - [NVIDIA Triton Inference Server](https://www.aguasto.com/inference-stack/triton) - [AMD ROCm](https://www.aguasto.com/inference-stack/rocm) - [Ray Serve](https://www.aguasto.com/inference-stack/ray-serve) - [Kubernetes GPU orchestration — NVIDIA device plugin](https://www.aguasto.com/inference-stack/kubernetes) - [Model weights are only the beginning of the memory budget](https://www.aguasto.com/learn/model-weights-and-runtime-memory) - [Why tokens per second is not enough to benchmark inference](https://www.aguasto.com/research/inference-benchmark-methodology) - [Prefill, decode and the cost of separating them](https://www.aguasto.com/learn/prefill-decode-and-disaggregated-serving) - [Choosing between vLLM, SGLang and TensorRT-LLM](https://www.aguasto.com/learn/choosing-an-inference-serving-framework) - [From Power to Inference—Building a Distributed AI Compute Network](https://www.aguasto.com/learn/from-power-to-inference) - [Dedicated compute and shared inference: compare the whole workload](https://www.aguasto.com/insights/dedicated-and-shared-inference-economics) - [Distributed inference reliability begins with the failure boundary](https://www.aguasto.com/learn/distributed-inference-reliability) - [Core Scientific: reading contracted, energized and billed capacity](https://www.aguasto.com/research/cases/core-scientific-capacity-disclosures) - [Why Modular AI Infrastructure Matters Now](https://www.aguasto.com/research/why-modular-ai-infrastructure-matters-now) - [Official LinkedIn](https://www.linkedin.com/company/aguasto) This is a generated representation of the public HTML page. Diagrams are conceptual. GPU and inference services are planned and are not currently available to book or call. The contact page describes the available inquiry flow.