Gemma 3 1B Instruct
GoogleGemmaОткрытые весаGemma · Коммерческое использование
Описание
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.
Дата выхода
2025-03-13
Параметры
1.0B
Длина контекста
—
Модальности
—
Радар способностей
5
general
1
coding
11
reasoning
12
science
8
agents
0
multimodal
Рейтинги
| Домен | #Место | Оценка | Источник |
|---|---|---|---|
| Рейтинг кодинга | 549 | 1.0 | AA |
| Общий рейтинг | 573 | 6.0 | AA |
| Наука | 560 | 8.0 | AA |
Оценки бенчмарков (LLM Stats)
(LLM Stats (zeroeval))Biology
GPQANYU + Cohere + Anthropic (2023)
19.2%Сам.
Code
HumanEvalOpenAI (2021)
41.5%Сам.
LiveCodeBench
1.9%Сам.
Factuality
FACTS Grounding
36.4%Сам.
SimpleQA
2.2%Сам.
Finance
MMLU-Pro
14.7%Сам.
General
IFEvalGoogle Research (2023)
80.2%Сам.
Natural2Code
56.0%Сам.
MBPP
0.35 / 100Сам.
Global-MMLU-Lite
34.2%Сам.
BIG-Bench Extra Hard
7.2%Сам.
Language
BIG-Bench Hard
39.1%Сам.
WMT24++
35.9%Сам.
ECLeKTic
1.4%Сам.
Math
GSM8k
62.8%Сам.
MATH
48.0%Сам.
HiddenMath
15.8%Сам.
Reasoning
Bird-SQL (dev)
6.4%Сам.
Индексы оценки AA
(Artificial Analysis)Math Index(Artificial Analysis)3.3
Intelligence Index(Artificial Analysis)1.0
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))0.5
Gpqa(NYU + Cohere + Anthropic (2023))0.2
Ifbench(Google Research (2023))0.2
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))0.1
Tau2(Sierra + U Toronto + Vector Institute (2025))0.1
Hle(Center for AI Safety + Scale AI (2025))0.1
Aime 25(MAA (Mathematical Association of America))0.0
Livecodebench(UC Berkeley + MIT + Cornell (2024))0.0
Scicode(UIUC + Argonne National Lab (2024))0.0
Aime(MAA (Mathematical Association of America))0.0
Lcr(Artificial Analysis)0.0
Terminalbench Hard(Stanford × Laude Institute (2026))0.0
Оценки категорий LLM Stats
(LLM Stats (zeroeval))Structured Output80
Instruction Following80
Math40
Grounding40
Reasoning30
General30
Physics20
Language20
Factuality20
Biology20
Chemistry20
Code20
Legal10
Finance10
Healthcare10
Цены
Цена вводаБесплатно
Цена выводаБесплатно
Смешанная цена (3:1)Бесплатно
Скорость
Токенов/сек0.0
Задержка первого токена0.00s
Время до первого ответа0.00s
Рейтинг цен провайдеров
Нет данных провайдеров