AIbase
EN
Home
AI Models Finder
Gemma 3 1B Instruct
G

Gemma 3 1B Instruct

Ultra-compact instruction-tuned model from Gemma 3 series with only 1B parameters but carefully optimized. Designed for edge deployment and resource-constrained environments, provides reliable instruction execution with minimal memory footprint. Supports 8K context window, suitable for mobile applications, IoT devices, and scenarios requiring local deployment, providing practical AI capabilities for lightweight applications.
Intelligence(Weak)
Speed(Slow)
Input Supported Modalities
Yes
Is Reasoning Model
32,000
Context Window
-
Maximum Output Tokens
-
Knowledge Cutoff
Go Compare

Pricing

- /M tokens
Input
- /M tokens
Output
- /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Gemini 2.0 Flash Thinking Experimental (Dec '24)
Gemini 1.5 Pro (Sep '24)
￥2.5
Gemini 2.0 Pro Experimental (Feb '25)

Basic Parameters

Gemma 3 1B InstructTechnical Parameters
Parameter Count
Not Announced
Context Length
32.00k tokens
Training Data Cutoff
Open Source Category
Open Weights (Permissive License)
Multimodal Support
Text Only
Throughput
Release Date
2025-03-13
Response Speed
0 tokens/s

Benchmark Scores

Below is the performance of Gemma 3 1B Instruct in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
13.42
Large Language Model Intelligence Level
Coding Index
1.19
Indicator of AI model performance on coding tasks
Math Index
24.2
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
13.5
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
23.7
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
5.2
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
1.7
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
0.7
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
32.4
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
48.4
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
-
An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase