Google has launched a newer model, Gemma 4 E4B, we suggest considering this model instead.

For more information, see Comparison of Gemma 4 E4B to other models and API provider benchmarks for Gemma 4 E4B.

Gemma 3 4B Instruct logo
Google
•

Open weights model

•

Released March 2025

Gemma 3 4B Instruct Intelligence, Performance & Price Analysis

API Provider Benchmarks

Model summary

IntelligenceUpdated

1
Artificial Analysis Intelligence Index
1 out of 4 units for Intelligence.

Speed

N/A
Output tokens per second
Unknown out of 4 units for Speed.

Input Price

$0.00
USD per 1M tokens
1 out of 4 units for Input Price.

Output Price

$0.00
USD per 1M tokens
1 out of 4 units for Output Price.

Verbosity

N/A
Output tokens from Intelligence Index
Unknown out of 4 units for Verbosity.

Gemma 3 4B Instruct is among the least intelligent models, but well priced when comparing to other open weight non-reasoning models of similar size. The model supports text and image input, outputs text, and has a 128k tokens context window.

Gemma 3 4B Instruct scores 1 on the Artificial Analysis Intelligence Index, placing it at the lower end among comparable models (averaging 3).

Pricing for Gemma 3 4B Instruct is $0.00 per 1M input tokens (competitively priced, average: $0.00) and $0.00 per 1M output tokens (competitively priced, average: $0.00).

ReasoningNo

This page shows the non-reasoning version of this model.

A reasoning variant may also exist.

Input modality

Supports: text, image

Output modality

Supports: text

Context window128k
~192 A4 pages of size 12 Arial font
Total parameters4.3B
LicenseGemma license
Model weightsHugging Face

Metrics are compared against models of the same class:

  • Non-reasoning models → compared only with other non-reasoning models
  • Reasoning models → compared across both reasoning and non-reasoning
  • Open weights models → compared only with other open weights models of the same size class:
    • Tiny: ≤4B parameters
    • Small: 4B–40B parameters
    • Medium: 40B–150B parameters
    • Large: >150B parameters
  • Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
    • <$0.15 per 1M tokens
    • $0.15–$1 per 1M tokens
    • >$1 per 1M tokens

Highlights

Updated

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Cost per Task

Weighted average cost (USD) per Intelligence Index task · Lower is better

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Estimate (independent evaluation forthcoming)
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Estimate (independent evaluation forthcoming)
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if the weights are available but commercial use is limited (typically requires obtaining a paid license).

Intelligence Breakdown

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
GDPval-AA v2

Agentic real-world work tasks, (Elo-500)/2000

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-BriefcaseNew

Agentic knowledge work, Elo

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon.

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

AA-Omniscience

AA-Omniscience Index

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.
Reasoning models are indicated by a lightbulb icon

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.

Openness

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)
Reasoning models are indicated by a lightbulb icon

Intelligence Index Comparisons

Intelligence vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Reasoning models are indicated by a lightbulb icon.

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Price and Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better
Reasoning models are indicated by a lightbulb icon

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index
Reasoning models are indicated by a lightbulb icon

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)
Reasoning models are indicated by a lightbulb icon

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Price per token included in the request/message sent to the API, represented as USD per million Tokens.

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

  • Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
  • Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
  • OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

Price per token generated by the model (received from the API), represented as USD per million Tokens.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Context Window

Context Window

Context window: tokens limit · Higher is better
Reasoning models are indicated by a lightbulb icon

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Model Size (Open Weights Models Only)

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference
Reasoning models are indicated by a lightbulb icon

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

Frequently Asked Questions

Common questions about Gemma 3 4B Instruct

Gemma 3 4B Instruct was released on March 12, 2025.

Gemma 3 4B Instruct was created by Google.

Gemma 3 4B Instruct scores 1 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 3).

No, Gemma 3 4B Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

Gemma 3 4B Instruct supports text and image input.

Gemma 3 4B Instruct supports text output.

Yes, Gemma 3 4B Instruct supports image input and can analyze, describe, and answer questions about images.

Yes, Gemma 3 4B Instruct is multimodal. It can process text and image input and generate text output.

Gemma 3 4B Instruct has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, Gemma 3 4B Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.

Gemma 3 4B Instruct has 4.3 billion parameters.

Gemma 3 4B Instruct is released under the Gemma license license. This license allows commercial use. View license

Gemma 3 4B Instruct achieves a score of 1 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Gemma 3 4B Instruct is available via API through 3 providers. Compare API providers

Gemma 3 4B Instruct is available through 3 API providers. Compare providers