Model Comparison

Gemma 3 27B vs Gemma 3 4B

Gemma 3 27B significantly outperforms across most benchmarks. Gemma 3 4B is 5.0x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

26 benchmarks

Gemma 3 27B outperforms in 26 benchmarks (AI2D, BIG-Bench Extra Hard, BIG-Bench Hard, Bird-SQL (dev), ChartQA, DocVQA, ECLeKTic, FACTS Grounding, Global-MMLU-Lite, GPQA, GSM8k, HiddenMath, HumanEval, IFEval, InfoVQA, LiveCodeBench, MATH, MathVista-Mini, MBPP, MMLU-Pro, MMMU (val), Natural2Code, SimpleQA, TextVQA, VQAv2 (val), WMT24++), while Gemma 3 4B is better at 0 benchmarks.

Gemma 3 27B significantly outperforms across most benchmarks.

Tue May 19 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Gemma 3 4B costs less

For input processing, Gemma 3 27B ($0.10/1M tokens) is 5.0x more expensive than Gemma 3 4B ($0.02/1M tokens).

For output processing, Gemma 3 27B ($0.20/1M tokens) is 5.0x more expensive than Gemma 3 4B ($0.04/1M tokens).

In conclusion, Gemma 3 27B is more expensive than Gemma 3 4B.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Tue May 19 2026 • llm-stats.com
Google
Gemma 3 27B
Input tokens$0.10
Output tokens$0.20
Best providerDeepinfra
Google
Gemma 3 4B
Input tokens$0.02
Output tokens$0.04
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

23.0B diff

Gemma 3 27B has 23.0B more parameters than Gemma 3 4B, making it 575.0% larger.

Google
Gemma 3 27B
27.0Bparameters
Google
Gemma 3 4B
4.0Bparameters
27.0B
Gemma 3 27B
4.0B
Gemma 3 4B

Context Window

Maximum input and output token capacity

Both models have the same input context window of 131,072 tokens. Both models can generate responses up to 131,072 tokens.

Google
Gemma 3 27B
Input131,072 tokens
Output131,072 tokens
Google
Gemma 3 4B
Input131,072 tokens
Output131,072 tokens
Tue May 19 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Gemma 3 27B and Gemma 3 4B support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Gemma 3 27B

Text
Images
Audio
Video

Gemma 3 4B

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under Gemma.

Both models share the same licensing terms, providing consistent usage rights.

Gemma 3 27B

Gemma

Open weights

Gemma 3 4B

Gemma

Open weights

Release Timeline

When each model was launched

Both models were released on 2025-03-12.

They likely represent similar generations of model development.

Gemma 3 27B

Mar 12, 2025

1.2 years ago

Gemma 3 4B

Mar 12, 2025

1.2 years ago

Knowledge Cutoff

When training data ends

Gemma 3 4B has a documented knowledge cutoff of 2024-08-01, while Gemma 3 27B's cutoff date is not specified.

We can confirm Gemma 3 4B's training data extends to 2024-08-01, but cannot make a direct comparison without Gemma 3 27B's cutoff date.

Gemma 3 27B

—

Gemma 3 4B

Aug 2024

Provider Availability

Gemma 3 27B is available from DeepInfra, Novita. Gemma 3 4B is available from DeepInfra.

Gemma 3 27B

deepinfra logo
Deepinfra
Input Price:Input: $0.10/1MOutput Price:Output: $0.20/1M
novita logo
Novita
Input Price:Input: $0.11/1MOutput Price:Output: $0.20/1M

Gemma 3 4B

deepinfra logo
Deepinfra
Input Price:Input: $0.02/1MOutput Price:Output: $0.04/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Google
Higher AI2D score (84.5% vs 74.8%)
Higher BIG-Bench Extra Hard score (19.3% vs 11.0%)
Higher BIG-Bench Hard score (87.6% vs 72.2%)
Higher Bird-SQL (dev) score (54.4% vs 36.3%)
Higher ChartQA score (78.0% vs 68.8%)
Higher DocVQA score (86.6% vs 75.8%)
Higher ECLeKTic score (16.7% vs 4.6%)
Higher FACTS Grounding score (74.9% vs 70.1%)
Higher Global-MMLU-Lite score (75.1% vs 54.5%)
Higher GPQA score (42.4% vs 30.8%)
Higher GSM8k score (95.9% vs 89.2%)
Higher HiddenMath score (60.3% vs 43.0%)
Higher HumanEval score (87.8% vs 71.3%)
Higher IFEval score (90.4% vs 90.2%)
Higher InfoVQA score (70.6% vs 50.0%)
Higher LiveCodeBench score (29.7% vs 12.6%)
Higher MATH score (89.0% vs 75.6%)
Higher MathVista-Mini score (67.6% vs 50.0%)
Higher MBPP score (74.4% vs 63.2%)
Higher MMLU-Pro score (67.5% vs 43.6%)
Higher MMMU (val) score (64.9% vs 48.8%)
Higher Natural2Code score (84.5% vs 70.3%)
Higher SimpleQA score (10.0% vs 4.0%)
Higher TextVQA score (65.1% vs 57.8%)
Higher VQAv2 (val) score (71.0% vs 62.4%)
Higher WMT24++ score (53.4% vs 46.8%)
Google
Less expensive input tokens
Less expensive output tokens

Detailed Comparison

AI Model Comparison Table
Feature
Google
Gemma 3 27B
Google
Gemma 3 4B

FAQ

Common questions about Gemma 3 27B vs Gemma 3 4B.

Which is better, Gemma 3 27B or Gemma 3 4B?

Gemma 3 27B significantly outperforms across most benchmarks. Gemma 3 27B is made by Google and Gemma 3 4B is made by Google. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Gemma 3 27B compare to Gemma 3 4B in benchmarks?

Gemma 3 27B scores GSM8k: 95.9%, IFEval: 90.4%, MATH: 89.0%, HumanEval: 87.8%, BIG-Bench Hard: 87.6%. Gemma 3 4B scores IFEval: 90.2%, GSM8k: 89.2%, DocVQA: 75.8%, MATH: 75.6%, AI2D: 74.8%.

Is Gemma 3 27B cheaper than Gemma 3 4B?

Gemma 3 4B is 5.0x cheaper for input tokens. Gemma 3 27B costs $0.10/M input and $0.20/M output via deepinfra. Gemma 3 4B costs $0.02/M input and $0.04/M output via deepinfra.

What are the context window sizes for Gemma 3 27B and Gemma 3 4B?

Gemma 3 27B supports 131K tokens and Gemma 3 4B supports 131K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Gemma 3 27B and Gemma 3 4B?

Key differences include input pricing ($0.10 vs $0.02/M). See the full comparison above for benchmark-by-benchmark results.