Google: Gemma 3 4B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning,…

google/gemma-3-4b-it

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.

Specifications & capabilities

Input
text, image
Output
text
Context window · tokens
131072
Knowledge cutoff
2024-08-31
Published model ID
gemma3@gemma-3-4b-it
Capabilities
multimodal, structuredOutputs, toolCalling, visionInput
Description source ↗

Evaluations

41–60 / 170

MMBench

51.8%

source id
mmBench
leaderboard name
image_quality
dimension
vision
metric
image_quality
rank
123
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
image_quality
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
163
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

81.5%

source id
mmBench
leaderboard name
nature_relation
dimension
vision
metric
nature_relation
rank
124
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_V11_Data
verified
Yes
metric_kind
nature_relation
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
295
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

78.2%

source id
mmBench
leaderboard name
celebrity_recognition
dimension
vision
metric
celebrity_recognition
rank
126
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_V11_Data
verified
Yes
metric_kind
celebrity_recognition
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
295
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

83.8%

source id
mmBench
leaderboard name
attribute_recognition
dimension
vision
metric
attribute_recognition
rank
127
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
attribute_recognition
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
162
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

43.9%

source id
mmBench
leaderboard name
calligraphy_painting
dimension
vision
metric
calligraphy_painting
rank
128
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
CCBench_Data
verified
Yes
metric_kind
calligraphy_painting
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
233
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

43.6%

source id
mmBench
leaderboard name
attribute_comparison
dimension
vision
metric
attribute_comparison
rank
128
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
attribute_comparison
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
163
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

79.2%

source id
mmBench
leaderboard name
CP
dimension
vision
metric
CP
rank
129
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
CP
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
236
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

54.1%

source id
mmBench
leaderboard name
image_quality
dimension
vision
metric
image_quality
rank
130
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
image_quality
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
162
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

89.1%

source id
mmBench
leaderboard name
image_scene
dimension
vision
metric
image_scene
rank
131
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
image_scene
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
162
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

51.4%

source id
mmBench
leaderboard name
LR
dimension
vision
metric
LR
rank
131
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
LR
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
236
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

77.4%

source id
mmBench
leaderboard name
AR
dimension
vision
metric
AR
rank
132
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
AR
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
236
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

53.8%

source id
mmBench
leaderboard name
LR
dimension
vision
metric
LR
rank
132
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
LR
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
235
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

69.7%

source id
mmBench
leaderboard name
Overall
dimension
vision
metric
Overall
rank
134
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
Overall
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
236
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

69.7%

source id
mmBench
leaderboard name
RR
dimension
vision
metric
RR
rank
135
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
RR
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
235
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

27.2%

source id
mmBench
leaderboard name
spatial_relationship
dimension
vision
metric
spatial_relationship
rank
137
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
spatial_relationship
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
162
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

68.8%

source id
mmBench
leaderboard name
FP-S
dimension
vision
metric
FP-S
rank
138
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_Data
verified
Yes
metric_kind
FP-S
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
236
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

43.6%

source id
mmBench
leaderboard name
attribute_comparison
dimension
vision
metric
attribute_comparison
rank
139
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
attribute_comparison
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
162
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

40.4%

source id
mmBench
leaderboard name
physical_relation
dimension
vision
metric
physical_relation
rank
139
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_Data
verified
Yes
metric_kind
physical_relation
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
162
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

37.4%

source id
mmBench
leaderboard name
food_clothes
dimension
vision
metric
food_clothes
rank
141
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
CCBench_Data
verified
Yes
metric_kind
food_clothes
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
233
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

MMBench

88.9%

source id
mmBench
leaderboard name
function_reasoning
dimension
vision
metric
function_reasoning
rank
142
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_CN_V11_Data
verified
Yes
metric_kind
function_reasoning
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
295
benchmark_evaluation
true
source model id
Gemma3-4B
Original result ↗

Published prices

1–6 / 6

gemma-3-4b-it ↗

$0.03

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
input_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Input tokens (per 1M)

gemma-3-4b-it ↗

$0.07

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
output_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Output tokens (per 1M)

google/gemma-3-4b-it ↗

$0.05

Inference provider
deepInfra
Platform
DeepInfra
Unit
input_tokens_per_million
Currency
USD
Billing conditions

google/gemma-3-4b-it ↗

$0.10

Inference provider
deepInfra
Platform
DeepInfra
Unit
output_tokens_per_million
Currency
USD
Billing conditions

google/gemma-3-4b-it ↗

$0.05

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

google/gemma-3-4b-it ↗

$0.10

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

Provider specifications & access

1–5 / 5

gemma-3-4b-it ↗

source model id
gemma-3-4b-it
hosting
gateway
platforms
  • Cheaper Inference
context length
128000
max output tokens
8000
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • structuredOutputs
  • toolCalling
  • visionInput

Gemma 3 4B IT ↗

source model id
google.gemma-3-4b-it
hosting
bedrock-managed
platforms
  • Amazon Bedrock
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities

    google/gemma-3-4b-it ↗

    source model id
    google/gemma-3-4b-it
    hosting
    nvidia-inference-listed
    platforms
    • NVIDIA inference catalog
    architecture
    input_modalities
      output_modalities
        capabilities
          availability
          Listed by inference API; runtime availability unverified

          gemma-3-4b-it ↗

          source model id
          publishers/google/models/gemma3@gemma-3-4b-it
          hosting
          vertex-self-deployed
          platforms
          • Google Cloud Vertex AI
          architecture
          input_modalities
          • image
          • text
          output_modalities
          • text
          capabilities
          • multimodal
          • visionInput

          google/gemma-3-4b-it ↗

          source model id
          publishers/hf-google/models/gemma-3-4b-it@001
          hosting
          vertex-self-deployed
          platforms
          • Google Cloud Vertex AI
          architecture
          input_modalities
          • image
          • text
          output_modalities
          • text
          capabilities
          • multimodal
          • visionInput

          Safety assessments

          1–1 / 1

          Foundation Model Transparency Index 2025 ↗

          41 / 100

          source id
          stanfordFMTI
          canonical model id
          google/gemma-3-4b-it
          taxonomy
          transparency
          hazard category
          transparency
          hazard name
          Organization transparency
          policy area
          Google
          assessment type
          organization-level disclosure
          metric
          disclosure_score
          result label
          41 / 100
          sample size
          100
          updated at
          2026-11-09T18:08:05.227Z

          Source specification observations

          1–3 / 3

          openRouter ↗

          field
          context_length
          value
          131072
          normalized value
          131072
          scope
          source-model
          source id
          openRouter
          confidence
          1

          openRouter ↗

          field
          knowledge_cutoff
          reported field
          knowledge_cutoff
          value
          2024-08-31
          normalized value
          2024-08-31
          precision
          day
          scope
          source-model
          source id
          openRouter
          confidence
          1

          openRouter ↗

          field
          max_output_tokens
          value
          16384
          normalized value
          16384
          scope
          source-model
          source id
          openRouter
          confidence
          1

          Original sources

          1–20 / 50

          storage.googleapis.com · Model reference ↗

          Hugging Face · google/gemma-3-4b-it ↗

          DeepInfra · Model page ↗

          Google Cloud · Model page ↗

          Google Cloud · Model page ↗

          OpenRouter · Model page ↗

          arXiv · Paper · 1705.03551 ↗

          arXiv · Paper · 1810.12440 ↗

          arXiv · Paper · 1903.00161 ↗

          arXiv · Paper · 1904.09728 ↗

          arXiv · Paper · 1905.07830 ↗

          arXiv · Paper · 1905.10044 ↗

          arXiv · Paper · 1907.10641 ↗

          arXiv · Paper · 1908.02660 ↗

          arXiv · Paper · 1910.11856 ↗

          arXiv · Paper · 1911.01547 ↗

          arXiv · Paper · 1911.11641 ↗

          arXiv · Paper · 2009.03300 ↗

          arXiv · Paper · 2103.03874 ↗

          arXiv · Paper · 2104.12756 ↗

          Source links

          1–15 / 15

          Hugging Face model card

          1–1 / 1

          Explore more models

          Models

          Loading
          EVIDENCE / COMPARISON

          Benchmarks

          Explore every benchmark

          Loading

          These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

          Install TensorTrace