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
101–120 / 170
94.7%
- source id
- mmBench
- leaderboard name
- identity_reasoning
- dimension
- vision
- metric
- identity_reasoning
- rank
- 210
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_Data
- verified
- Yes
- metric_kind
- identity_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 ↗35.8%
- source id
- mmBench
- leaderboard name
- structuralized_imagetext_understanding
- dimension
- vision
- metric
- structuralized_imagetext_understanding
- rank
- 210
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_Data
- verified
- Yes
- metric_kind
- structuralized_imagetext_understanding
- 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 ↗84.3%
- source id
- mmBench
- leaderboard name
- attribute_recognition
- dimension
- vision
- metric
- attribute_recognition
- rank
- 211
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_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
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-4B
Original result ↗49.4%
- source id
- mmBench
- leaderboard name
- physical_property_reasoning
- dimension
- vision
- metric
- physical_property_reasoning
- rank
- 214
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_CN_V11_Data
- verified
- Yes
- metric_kind
- physical_property_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 ↗1,280.566
- source id
- lmarena
- leaderboard name
- LMArena Text German
- dimension
- general
- metric
- Arena rating
- rank
- 215
- sample size
- 162
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 4B IT
- confidence lower
- 1238.4378640448997
- confidence upper
- 1322.6944104321965
Original result ↗86.7%
- source id
- mmBench
- leaderboard name
- ocr
- dimension
- vision
- metric
- ocr
- rank
- 216
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_Data
- verified
- Yes
- metric_kind
- ocr
- 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 ↗64.7%
- source id
- mmBench
- leaderboard name
- RR
- dimension
- vision
- metric
- RR
- rank
- 218
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_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
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-4B
Original result ↗1,341.889
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Medicine And Healthcare
- dimension
- general
- metric
- Arena rating
- rank
- 221
- sample size
- 197
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 4B IT
- confidence lower
- 1303.6797570053095
- confidence upper
- 1380.0989781838557
Original result ↗33.9%
- source id
- mmBench
- leaderboard name
- image_quality
- dimension
- vision
- metric
- image_quality
- rank
- 224
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_CN_V11_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
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-4B
Original result ↗54.3%
- source id
- mmBench
- leaderboard name
- FP-C
- dimension
- vision
- metric
- FP-C
- rank
- 229
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_CN_V11_Data
- verified
- Yes
- metric_kind
- FP-C
- 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 ↗41.3%
- source id
- mmBench
- leaderboard name
- attribute_comparison
- dimension
- vision
- metric
- attribute_comparison
- rank
- 229
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_CN_V11_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
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-4B
Original result ↗1,354.012
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Medicine And Healthcare
- dimension
- style
- metric
- Arena rating
- rank
- 233
- sample size
- 197
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 4B IT
- confidence lower
- 1315.8223985622644
- confidence upper
- 1392.201622780296
Original result ↗66.1%
- source id
- mmBench
- leaderboard name
- Overall
- dimension
- vision
- metric
- Overall
- rank
- 233
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_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
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-4B
Original result ↗1,290.283
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control German
- dimension
- style
- metric
- Arena rating
- rank
- 234
- sample size
- 162
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 4B IT
- confidence lower
- 1248.3399958190869
- confidence upper
- 1332.2251434706286
Original result ↗1,327.258
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Legal And Government
- dimension
- general
- metric
- Arena rating
- rank
- 235
- sample size
- 245
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 4B IT
- confidence lower
- 1291.5339705876127
- confidence upper
- 1362.9822685266556
Original result ↗1,310.806
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Business And Management And Financial Operations
- dimension
- general
- metric
- Arena rating
- rank
- 235
- sample size
- 390
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 4B IT
- confidence lower
- 1280.7815513147689
- confidence upper
- 1340.8302744672226
Original result ↗71.1%
- source id
- mmBench
- leaderboard name
- CP
- dimension
- vision
- metric
- CP
- rank
- 238
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_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
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-4B
Original result ↗35.5%
- source id
- mmBench
- leaderboard name
- image_quality
- dimension
- vision
- metric
- image_quality
- rank
- 239
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- MMBench_TEST_EN_V11_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
- 295
- benchmark_evaluation
- true
- source model id
- Gemma3-4B
Original result ↗1,330.167
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Business And Management And Financial Operations
- dimension
- style
- metric
- Arena rating
- rank
- 240
- sample size
- 390
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 4B IT
- confidence lower
- 1300.1854065084385
- confidence upper
- 1360.1492761733657
Original result ↗1,293.815
- source id
- lmarena
- leaderboard name
- LMArena Text Russian
- dimension
- general
- metric
- Arena rating
- rank
- 241
- sample size
- 307
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemma 3 4B IT
- confidence lower
- 1263.3909122511873
- confidence upper
- 1324.2395217426406
Original result ↗Published prices
1–6 / 6
$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)
$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)
$0.05
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- input_tokens_per_million
- Currency
- USD
$0.10
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- output_tokens_per_million
- Currency
- USD
$0.05
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.10
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
Provider specifications & access
1–5 / 5
- source model id
- gemma-3-4b-it
- hosting
- gateway
- context length
- 128000
- max output tokens
- 8000
- capabilities
- structuredOutputs
- toolCalling
- visionInput
- source model id
- google.gemma-3-4b-it
- hosting
- bedrock-managed
- source model id
- google/gemma-3-4b-it
- hosting
- nvidia-inference-listed
- availability
- Listed by inference API; runtime availability unverified
- source model id
- publishers/google/models/gemma3@gemma-3-4b-it
- hosting
- vertex-self-deployed
- source model id
- publishers/hf-google/models/gemma-3-4b-it@001
- hosting
- vertex-self-deployed
Safety assessments
1–1 / 1
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
- field
- context_length
- value
- 131072
- normalized value
- 131072
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- 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
- field
- max_output_tokens
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- openRouter
- confidence
- 1
Hugging Face model card
1–1 / 1
- downloads
- 1002104
- likes
- 1673
- pipeline tag
- image-text-to-text
- library name
- transformers
- License
- gemma
Explore more models