Google model product
5 billion effective parameters (8B with embeddings) and a 128K context window.
Updated Aug 12, 2026. Default version: Gemma 4 E4B
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Gemma 4 E4B.
| BIG-Bench Extra Hard | 33.1% | 05 | 11 | 60.0% | C | |
| MedXpertQA | 28.7% | 10 | 12 | 18.2% | C | |
| MRCR v2 (8-needle) | 25.4% | 16 | 21 | 25.0% | C | |
| AIME 2026 | 42.5% | 17 | 18 | 5.9% | C | |
| t2-bench | 57.5% | 19 | 23 | 18.2% | C | |
| MathVision | 59.5% | 24 | 32 | 25.8% | C | |
| MMMLU | 76.6% | 41 | 49 | 16.7% | C | |
| LiveCodeBench v6 | 52.0% | 43 | 53 | 19.2% | C | |
| MMMU-Pro | 52.6% | 57 | 66 | 13.8% | C | |
| MMLU-Pro | 69.4% | 83 | 129 | 35.9% | C | |
| GPQA | 58.6% | 163 | 234 | 30.5% | C |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Provider-specific output speed and catalog latency for Gemma 4 E4B. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Official vendor API pricing appears first, followed by individual provider offers.
| Deep Infra | google/gemma-4-E4B-it | global | $0.02 | $0.10 | 131.1K | |
| NanoGPT | gemma-4-e4b-it | global | $0.04 | $0.20 | 131.1K | |
| Pioneer | google/gemma-4-E4B-it | global | $0.20 | $0.20 | 32.8K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Available versions of this model. The score column identifies the version used in the overall ranking.
| Gemma 4 E4B | 24.4 | 8B | 131.1K | 8.2K | Yes | Apache 2.0 |
Key information about Gemma 4 E4B and its available data.
5 billion effective parameters (8B with embeddings) and a 128K context window. Supports image, text, and audio inputs. Features Per-Layer Embeddings for efficient on-device deployment while maintaining strong multimodal capabilities.
Data as of 2026-08-11.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Common questions about Gemma 4 E4B.
Gemma 4 E4B's default version was released on Apr 2, 2026.
No official standard PAYG price is currently available for Gemma 4 E4B. The lowest tracked third-party offer starts at $0.02 input and $0.10 output via Deep Infra.
Gemma 4 E4B was created by Google.
The default version has a 131.1K token context window.
Yes. The default version is marked as open weight under Apache 2.0.
3 provider offerings are linked to the default version.
Nearby ranked alternatives include Qwen3 VL 8B, GPT-4.1-mini, Llama 3.1 405B.