Sovereign inference — Gemma 3 27B
Your sovereign, private Gemma 3 27B
A reasoning model in the medium tier, served on ToothFairyAI's AU, EU and US endpoints — private by default, billed in Units of Intelligence at the published rates below. No training on your data, no vendor lock-in.
AU · EU · US resident0.43 UoI/1M input1.51 UoI/1M output131K context
How Gemma 3 27B compares
Independent intelligence index for Gemma 3 27B against every peer in the Medium tier (and the tier above where needed) — same source, same tests.
Latency — end-to-end seconds for a 500-token answer
Capability indexes
Domain-weighted agentic performance for Gemma 3 27B.
Capability index vs medium peers
Finance & AccountingStrategy & OpsLegalEngineeringEconomics
The evaluations behind the index
Independent benchmark results for Gemma 3 27B — Elo scores as published; pass rates shown as percentages.
Per-evaluation economics
| Evaluation | Score | Time / task | Output tokens / task |
|---|---|---|---|
| AA-Briefcase | 0.0% | — | 41833 |
| GDPval-AA | -42439.0% | — | 21362 |
| AutomationBench-AA | 0.2% | — | 230 |
| Terminal-Bench 4.0 | 0.0% | — | 287 |
| SciCode | 23.3% | — | 508 |
| Humanity's Last Exam | 4.4% | — | 720 |
| GDP.pdf | 0.2% | — | 618 |
| CritPt | 0.0% | — | 2438 |
| AA-Omniscience | -6721.7% | — | 9 |
| AA-LCR (long context) | 7.3% | — | 260 |
Run Gemma 3 27B privately
One key, one endpoint, three jurisdictions.
- Size tierMedium
- Input rate0.43 UoI/1M
- Output rate1.51 UoI/1M
- Cached input rate—
- Context window131K tokens
- Max output8K tokens
- ReasoningYes — emits thinking traces
- Vision & video inputSupports image input
- Tool callingSupported
- Data residencyAU, EU and US endpoints — processing stays inside the region you call
Copyright 2026 ToothFairyAI PTY LTD. All Rights Reserved.
