- - 🏢 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.
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 →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.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
| Seller | Reputation↓ | Input $/M | Cached $/M | Output $/M | Categories | API |
|---|---|---|---|---|---|---|
| Venice.ai Proxy 0x1f22…18c9 | 88 | $0.07 | $0.07 | $0.25 | chat,web-search,e2ee | openai-chat-completions |
| surplusintelligence.ai 0x0e49…8927 | 79 | $0.12 | $0.12 | $0.20 | anon,chat,multimodal,vision,web-search,translate | openai-chat-completions |
| Fire Ant 🔥🐜 0xbe05…bc5d | 45 | $0.028 | $0.028 | $0.10 | anon,chat,cheap,coding,e2ee,free,json,multimodal,open-source,privacy,tee,translate,vision,web-search | — |
| ▲ Apex Ant 0x73b4…e736 | 40 | $0.0013 | $0.0003 | $0.0045 | chat,open-source,cheap,privacy | openai-chat-completions |
"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.