Saltar al contenido principal
AITier

Gemma 3 1B Instruct

GoogleGemmaOpen WeightGemma · Commercial OK

Descripción

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.

Fecha de lanzamiento
2025-03-13
Parámetros
1.0B
Longitud del contexto
—
Modalidades
—

Radar de capacidades

8
general
1
coding
11
reasoning
12
scienceest.
0
agents
0
multimodal

Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.

Rankings

Dominio#PosiciónPuntuaciónFuente
Code Ranking482
0.0
AA
General Ranking497
7.0
AA
Math Reasoning336
11.0
AA
Reasoning105
6.0
LS
Science478
9.0
AA

Puntuaciones de benchmarks (LLM Stats)

Biology

GPQA19.2%Aut.

Code

HumanEval41.5%Aut.
LiveCodeBench1.9%Aut.

Factuality

FACTS Grounding36.4%Aut.
SimpleQA2.2%Aut.

Finance

MMLU-Pro14.7%Aut.

General

IFEval80.2%Aut.
Natural2Code56.0%Aut.
MBPP0.35 / 100Aut.
Global-MMLU-Lite34.2%Aut.
BIG-Bench Extra Hard7.2%Aut.

Language

BIG-Bench Hard39.1%Aut.
WMT24++35.9%Aut.
ECLeKTic1.4%Aut.

Math

GSM8k62.8%Aut.
MATH48.0%Aut.
HiddenMath15.8%Aut.

Reasoning

Bird-SQL (dev)6.4%Aut.

Índices de evaluación AA

Intelligence Index
5.5
Math Index
3.3
Math 500
0.5
Gpqa
0.2
Coding Index
0.2
Ifbench
0.2
Mmlu Pro
0.1
Tau2
0.1
Hle
0.1
Aime 25
0.0
Livecodebench
0.0
Scicode
0.0
Aime
0.0
Lcr
0.0
Terminalbench Hard
0.0

Puntuaciones por categoría LLM Stats

Structured Output
80
Instruction Following
80
Grounding
40
Math
40
General
30
Reasoning
30
Biology
20
Chemistry
20
Code
20
Factuality
20
Language
20
Physics
20
Finance
10
Healthcare
10
Legal
10

Precios

Precio de entradaGratis
Precio de salidaGratis
Precio mixto (3:1)Gratis

Velocidad

Tokens/seg61.3 tokens/s
Retraso del primer token0.66s
Tiempo hasta la respuesta0.66s

Proveedores disponibles

(Unidades internas LS)

No hay datos de proveedores disponibles

Fuentes externas

LLM Stats