Gemma 3 27B IT

Gemma 3 27B IT is the instruction-tuned flagship of Google's third-generation Gemma family, released on March 12, 2025 as an open-weight successor to Gemma 2. Its weights are published on Hugging Face under the Gemma License, with community-quantized GGUF builds (Q4_K_M, Q5_K_M, Q6_K, Q8_0) and an Ollama package making the model easy to run locally on consumer GPUs. It carries forward the architectural and training advances of Google's Gemini line, positioning the Gemma 3 series as a research-friendly counterpart aimed at developers who want state-of-the-art capability without closed-API constraints.

The model is multimodal on the input side, accepting both text and images while producing text outputs, and supports a context window that extends to roughly 128k tokens. Listed capabilities include structured outputs and function calling, enabling tool-augmented workflows and schema-driven generation alongside chat, reasoning, and math tasks. The combination of a long context, vision-language understanding, and developer-oriented tooling makes Gemma 3 27B IT a practical fit for assistants that need to reason over lengthy documents, mixed media inputs, or agentic pipelines that call external functions.

OpenRoutergoogle/gemma-3-27b-itgemma

Open provider page Provider docs

Quick Info

Provider: OpenRouter
Model key: google/gemma-3-27b-it
Release date: Mar 12, 2025
Last updated: Mar 12, 2025
Knowledge cutoff: 2024-08
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $0.08
Output token cost: $0.45

Limits

Output tokens: 117,964 tokens
Context window: 131,072 tokens

Transparent token rates

Compare Gemma 3 27B IT pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Gemma 3 27B IT

OpenRouter

CoverageBenchmark

Pricepertoken's aggregator page confirms Gemma 3 27B was released March 12, 2025, with pricing starting at $0.080 per million input tokens and $0.160 per million output tokens, plus a cached input price of $0.040 per million tokens. The model supports a 128K-token context window and offers vision capabilities, tool use The page reports benchmark scores for Gemma 3 27B of Intelligence 7.4 (22nd percentile), Coding 10.1 (12th percentile), Math 20.7 (23rd percentile), and MMLU Pro 66.9 (33rd percentile), with a GPQA score of 42.8. Input prices across providers range from $0.080 to $0.900 per million tokens, and the model is positioned f

OpenRouter

CoverageBenchmark

Roboflow's playground page documents Gemma 3 27B as the largest open-weight model in Google's Gemma 3 family, released March 12, 2025. It is multimodal, accepting both text and images as input while producing text outputs, supports a 128,000-token context window, and typically generates up to 8,192 tokens in a single p The page provides deployment footprint specifics: the full BF16 model requires 46 GB of VRAM, while quantization-aware training (QAT) versions in 8-bit or 4-bit significantly reduce that footprint. It also reports a vision-evaluation legacy benchmark score of 58.21% pass rate across 67 tasks (ranking 51 of 77 models, b

OpenRouter

Official sourceBenchmark

OpenRouter's model page for google/gemma-3-27b-it confirms Gemma 3 27B is a multimodal vision-in/text-out model with a 131K context window, knowledge cutoff August 2024, and a listed price of $0.08 per million input tokens and $0.16 per million output tokens. Released March 12, 2025, it supports structured outputs, fun The page details OpenRouter's routed providers for Gemma 3 27B: DeepInfra at $0.08/$0.16 with 0.66s latency and 20 tps throughput, Parasail at $0.08/$0.45 with 39.1% cache hit rate and 24 tps (carrying 90.4% of token share), Nebius Token Factory at $0.10/$0.30 with 0.46s latency, and NovitaAI at $0.119/$0.20. The weigh

OpenRouter

Coverage

Access ChatGPT, Claude, Gemini & 350+ AI models in one platform. Generate images, videos, music & more. Get started today., Use Google: Gemma 3 27B (free) by Google on Krater.ai. Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles cont... Access 350+ AI models including Googl

OpenRouter

CoverageDiscourse

Hi dear Gemma-Team,