GoogleGoogle·text

Gemma 3 27B

E2eeWeb search
Quick reference
Gemma 3 27B — TLDR
  • - 🏢 Google's open-weight Gemma 3 27B, here in a confidential-computing deployment.
  • - 🔒 Runs in a Trusted Execution Environment with hardware attestation for verification.
  • - 👁️ Multimodal: accepts vision-language input, generates text output.
  • - 🌐 Understands 140+ languages via a Gemini-derived tokenizer.
  • - 📏 Natively supports up to 128K-token context (this deployment exposes 40,000).
  • - 🆕 Adds vision and far longer context versus text-only Gemma 2.
  • - 🔧 Improved function calling and structured outputs.
  • - 🧠 27B parameters, runnable on a single GPU with quantization.
💰 Best price on AntSeed
$0.0013 / $0.004599%
per 1M · cheapest in / out
📏 Context
40K tokens
🐜 Sellers
4
advertising on AntSeed
Provider

Google is an American multinational technology corporation and one of the world's most valuable brands. A subsidiary of parent company Alphabet Inc., Google operates across search, cloud computing, consumer electronics, and artificial intelligence. Its DeepMind and Google…

Explore 11 more models by Google
About this model

Gemma 3 27B is the largest model in Google's third-generation open Gemma family, offered here as a privacy-focused build that executes inside a Trusted Execution Environment, with hardware attestation evidence available so users can independently verify the runtime. The underlying model is a decoder-only transformer paired with a SigLIP vision encoder, letting it analyze images alongside text, support 140+ languages, and follow instructions with structured outputs and function calling.

Compared with its own predecessor, Gemma 2, the jump is substantial. Gemma 3 introduces multimodal vision-language understanding that Gemma 2 lacked, expands the context window from Gemma 2's 8K up to 128K tokens, and adopts a Gemini-style tokenizer for stronger multilingual coverage. Hugging Face's release notes describe an interleaved local-to-global attention design that cuts KV-cache memory during long-context inference relative to earlier Gemma designs.

On Google-reported evaluations in the model card, the 27B instruction-tuned model scores 67.5 on MMLU-Pro, 69.0 on MATH, 42.4 on GPQA Diamond, and 64.9 on MMMU. Within this catalog, it is part of a broader Google lineup that includes the newer [[sibling:e2ee-gemma-4-31b|Gemma 4 31B Instruct]] and the standard [[sibling:google-gemma-3-27b-it|Google Gemma 3 27B Instruct]] release, alongside siblings such as [[sibling:gemini-3-5-flash|Gemini 3.5 Flash]]. The Gemma license governs usage, and quantization-aware variants make local deployment on a single GPU feasible.

View source on GitHub ↗View model card on HuggingFace ↗
Sources
deepmind.googleGemma 3 — Google DeepMind· deepmind.googlehuggingface.cogoogle/gemma-3-27b-it · Hugging Face· huggingface.co

This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.

Sellers serving Gemma 3 27B (4)
SellerReputationInput $/MCached $/MOutput $/MCategoriesAPI

"Best price" and the seller table are live AntSeed catalog data (advertised $/1M tokens, not settled amounts). Reputation = on-chain trust (0-100). Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase.