Compare the listed model data for Gemma 3 27B by Google and Gemma 4 318B by Google. Benchmark and pricing records are not a controlled test and may change.
Data last updated: 2026-10-16. Verify current model details with each provider.
What the listed data says
Gemma 3 27B: 128K tokens; Gemma 4 318B: 1M tokens. Gemma 4 318B has the larger listed context window. Gemma 3 27B is listed for coding, vision, multimodal input, long-context tasks; Gemma 4 318B is listed for coding, reasoning, vision, multimodal input, long-context tasks. Shared catalog benchmark entries: MMLU: Gemma 3 27B 78.4%; Gemma 4 318B 87.2%; HumanEval: Gemma 3 27B 74.3%; Gemma 4 318B 85.8%; DocVQA: Gemma 3 27B 85.6%; Gemma 4 318B 93.1%. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
Catalog source links
Use these model and provider links to verify current specifications, pricing, and availability.
The first listed parameter quantities are 27B and 318B; the larger quantity is 11.78× the smaller. Total and active MoE parameters are not directly equivalent.
The catalog release dates are March 2025 and June 2025, about 3 months apart at the precision supplied.
Cost example: 1M input and 1M output tokens
A cost example for 1M input plus 1M output tokens cannot be calculated reliably because separate numeric input and output rates are not listed for both models.
Choose Gemma 3 27B if…
Choose Gemma 3 27B when your task aligns with catalog-listed uses or strengths such as Multimodal enterprise apps at deployable scale, Visual document analysis: receipts, invoices, charts, Multilingual applications, Google's open multimodal model at accessible 27B scale.
Choose Gemma 4 318B if…
Choose Gemma 4 318B when your task aligns with catalog-listed uses or strengths such as Enterprise multimodal AI requiring Google-grade quality, Long-document visual analysis: PDF, charts, slides, Multilingual enterprise AI serving global markets, Google's flagship open-weight model — brings DeepMind research quality to open deployment.
Catalog specifications for Gemma 3 27B and Gemma 4 318B
Specification
Gemma 3 27B
Gemma 4 318B
Provider
Google
Google
Parameters
27B
318B
Context window
128K tokens
1M tokens
Maximum output
Not listed
Not listed
Catalog pricing
Gemma Terms — free
Gemma Terms of Use — free for most uses
Listed input/output cost per 1M tokens
Separate numeric input/output rates not listed
Separate numeric input/output rates not listed
License
Gemma Terms of Use
Gemma Terms of Use
Coding support
Listed
Listed
Reasoning support
Not listed
Listed
Vision input
Listed
Listed
Multimodal
Listed
Listed
Open weights
Yes
Yes
Benchmark: MMLU
78.4%
87.2%
Benchmark: HumanEval
74.3%
85.8%
Benchmark: DocVQA
85.6%
93.1%
Figures are transcribed from LITHOVEX model records. Benchmark versions and evaluation setups may differ; pricing and specifications can change. Check each provider's current documentation before making a decision.
Frequently Asked Questions
What is different between Gemma 3 27B and Gemma 4 318B?
Gemma 3 27B: 128K tokens; Gemma 4 318B: 1M tokens. Gemma 4 318B has the larger listed context window. Gemma 3 27B is listed for coding, vision, multimodal input, long-context tasks; Gemma 4 318B is listed for coding, reasoning, vision, multimodal input, long-context tasks. Shared catalog benchmark entries: MMLU: Gemma 3 27B 78.4%; Gemma 4 318B 87.2%; HumanEval: Gemma 3 27B 74.3%; Gemma 4 318B 85.8%; DocVQA: Gemma 3 27B 85.6%; Gemma 4 318B 93.1%. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
What benchmark values are listed for Gemma 3 27B and Gemma 4 318B?
MMLU: Gemma 3 27B 78.4%; Gemma 4 318B 87.2%; HumanEval: Gemma 3 27B 74.3%; Gemma 4 318B 85.8%; DocVQA: Gemma 3 27B 85.6%; Gemma 4 318B 93.1%. The catalog values may use different versions and evaluation setups, so they are reference points rather than a controlled head-to-head result.
Which model has the larger listed context window?
Gemma 3 27B: 128K tokens; Gemma 4 318B: 1M tokens. Gemma 4 318B has the larger listed context window.
What are the listed costs per million tokens for Gemma 3 27B and Gemma 4 318B?
Gemma 3 27B: Separate numeric input/output rates not listed (Gemma Terms — free). Gemma 4 318B: Separate numeric input/output rates not listed (Gemma Terms of Use — free for most uses). Where separate numeric input and output rates are available, the worked example uses 1M input plus 1M output tokens. Confirm current terms with each provider.
How far apart are the listed release dates for Gemma 3 27B and Gemma 4 318B?
The catalog lists Gemma 3 27B as March 2025 and Gemma 4 318B as June 2025, about 3 months apart at the precision supplied.
When was the comparison data last updated?
The model catalog records 2026-10-16 as its data update date. Provider specifications and prices may have changed since then.
How should I choose between Gemma 3 27B and Gemma 4 318B?
Compare the listed specifications and capabilities, review the benchmark notes, then test both with the same representative prompt for your task. This page does not claim a universal winner.