The Gemma 3 1B model is a lightweight, 1-billion-parameter language model by Google, optimized for efficiency on resource-limited devices. At 529MB, it processes text at 2,585 tokens/second with a context window of 128,000 tokens. It supports 35+ languages but handles text-only input, unlike larger multimodal Gemma models. This balance of speed and efficiency makes it ideal for fast text processing on mobile and low-power devices.
发布日期2025年3月12日
参数规模1B
上下文长度—
许可证Gemma
知识截止—
Benchmarks
评测成绩
| 评测基准 | 类别 | 分数 | 来源 |
|---|---|---|---|
| IFEval | general | 80.2 | 来源 |
| GSM8k | math reasoning | 62.8 | 来源 |
| Natural2Code | reasoning general | 56.0 | 来源 |
| MATH | math reasoning | 48.0 | 来源 |
| HumanEval | reasoning code | 41.5 | 来源 |
| BIG-Bench Hard | reasoning math language | 39.1 | 来源 |
| FACTS Grounding | reasoning | 36.4 | 来源 |
| WMT24++ | language | 35.9 | 来源 |
| MBPP | reasoning general | 35.2 | 来源 |
| Global-MMLU-Lite | general language reasoning | 34.2 | 来源 |
| GPQA | reasoning general | 19.2 | 来源 |
| HiddenMath | math reasoning | 15.8 | 来源 |
| MMLU-Pro | language reasoning math general | 14.7 | 来源 |
| BIG-Bench Extra Hard | reasoning general language | 7.2 | 来源 |
| Bird-SQL (dev) | reasoning | 6.4 | 来源 |
| SimpleQA | general reasoning | 2.2 | 来源 |
| LiveCodeBench | reasoning general code | 1.9 | 来源 |
| ECLeKTic | language reasoning | 1.4 | 来源 |
Pricing
API 价格对比
暂无 API 价格。