Gemma 3 27B
Open Gemma instruction model for efficient chat and self-hosted deployments
Model facts
- Context window
- 131K tokens
- Maximum output
- 8K tokens
- Cheapest paid input
- $0.08 per 1M tokens
- Cheapest paid output
- $0.16 per 1M tokens
- Open weights
- yes
- Providers
- 11
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image, pdf.
Local hardware estimate
At 4K context: Q4_K_M 17.8 GiB, Q8_0 30.5 GiB, F16 54.5 GiB working memory.
- Parameters
- 27.4 billion
- Architecture
- gemma3
- Model license
- gemma
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 7.4 | 10.1 | 20.7 | not measured |
Observed price history
- 2026-08-24: $0.08 input / $0.16 output per 1M tokens
API providers
- Kilo Gateway (Google) — model id google/gemma-3-27b-it; $0.08 input / $0.16 output per 1M tokens; provider documentation
- NovitaAI — model id google/gemma-3-27b-it; $0.119 input / $0.2 output per 1M tokens; provider documentation
- Amazon Bedrock — model id google.gemma-3-27b-it; $0.12 input / $0.2 output per 1M tokens; provider documentation
- Venice AI — model id google-gemma-3-27b-it; $0.12 input / $0.2 output per 1M tokens; provider documentation
- Cortecs — model id gemma-3-27b-it; $0.099 input / $0.299 output per 1M tokens; provider documentation
- Nebius Token Factory — model id google/gemma-3-27b-it; $0.1 input / $0.3 output per 1M tokens; provider documentation
- OpenRouter — model id google/gemma-3-27b-it; $0.08 input / $0.45 output per 1M tokens; provider documentation
- NanoGPT — model id unsloth/gemma-3-27b-it; $0.299 input / $0.299 output per 1M tokens; provider documentation
- GreenPT — model id gemma-3-27b-it; $0.342 input / $0.684 output per 1M tokens; provider documentation
- STACKIT — model id google/gemma-3-27b-it; $0.53 input / $0.76 output per 1M tokens; provider documentation
- Arena — model id gemma-3-27b-it; not published input / not published output per 1M tokens; provider documentation