NOUMENOpen app
NOUMEN

Google · Open weights

Gemma 3 4B IT

Added Jan 1, 2024Open weights

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

Use in the app

Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.

  • PDF input
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.20
Output
$0.20

Reference prices as published by the model provider. API example

Specifications

Context window
128K
Max output
8.2K
Average output (7 days)
115 tokens
Longer than 11% of 465 models

Side by side

Compare models

Put Gemma 3 4B IT next to up to three other models. The comparison stays in the link, so you can share it.

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

TryMinistral 3BCohere: Command R+GPT-3.5 TurboAll 3

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

Intelligence Index

4.8

Better than 0% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    2.7

    Composite of the coding evaluations

    Better than 0% of 168 scored models

  • Math Index

    12.7

    Composite of the math evaluations

    Better than 11% of 118 scored models

Document reasoning

  • AA-LCRv1.1

    6.7%

    Reasoning across long documents

    Better than 3% of 309 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    5.3%

    Expert-level questions across academic fields

    Better than 17% of 323 scored models

  • GPQA Diamond

    29.1%

    Graduate-level science questions

    Better than 1% of 291 scored models

  • MMLU-Pro

    41.7%

    Multi-subject knowledge and reasoning

    Better than 0% of 132 scored models

  • IFBench

    28.3%

    Following precise output instructions

    Better than 3% of 215 scored models

Coding

  • LiveCodeBench

    11.2%

    Recent competitive programming problems

    Better than 0% of 129 scored models

Math

  • AIME 2025

    12.7%

    Competition mathematics, 2025 problems

    Better than 11% of 118 scored models

  • AIME

    6.3%

    Competition mathematics

    Better than 6% of 72 scored models

  • MATH-500

    76.6%

    Competition math problems

    Better than 24% of 73 scored models

Legacy evaluations

  • Terminal-Bench Hard

    0.8%

    Earlier terminal task suite

    Better than 1% of 212 scored models

  • τ²-Bench Telecom

    5.0%

    Tool use in a customer-support simulation

    Better than 0% of 214 scored models

  • AA-LCR (unversioned)

    6.7%

    Long-context reasoning, earlier grading

    Better than 3% of 309 scored models

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Request success (24h)
99.8%
Reliable
Hourly request success · last 72 hoursLowest hour 66.6%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "unsloth/gemma-3-4b-it",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="unsloth/gemma-3-4b-it",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.