Qwen: Qwen3 30B A3B Instruct 2507
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-qual…
qwen/qwen3-30b-a3b-instruct-2507
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 262144
- Knowledge cutoff
- 2025-06-30
- Published model ID
- Qwen3-30B-A3B-Instruct-2507
- Capabilities
- promptCaching, structuredOutputs, toolCalling
Description source ↗Evaluations
61–80 / 99
1,394.74
- source id
- lmarena
- leaderboard name
- LMArena Text Math
- dimension
- general
- metric
- Arena rating
- rank
- 172
- sample size
- 1391
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1379.6013926680994
- confidence upper
- 1409.8793057716518
Original result ↗1,353.134
- source id
- lmarena
- leaderboard name
- LMArena Text Polish
- dimension
- general
- metric
- Arena rating
- rank
- 173
- sample size
- 1541
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1337.904140892128
- confidence upper
- 1368.3638308518885
Original result ↗1,437.87
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Coding
- dimension
- style
- metric
- Arena rating
- rank
- 175
- sample size
- 4608
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1429.0138947934365
- confidence upper
- 1446.7269392778421
Original result ↗1,393.102
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Life And Physical And Social Science
- dimension
- general
- metric
- Arena rating
- rank
- 175
- sample size
- 3672
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1383.3048918186437
- confidence upper
- 1402.899304318977
Original result ↗1,386.836
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Legal And Government
- dimension
- general
- metric
- Arena rating
- rank
- 175
- sample size
- 1462
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1371.4459048522112
- confidence upper
- 1402.2252213368843
Original result ↗1,383.838
- source id
- lmarena
- leaderboard name
- LMArena Text Overall
- dimension
- general
- metric
- Arena rating
- rank
- 175
- sample size
- 23287
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1378.9555564794382
- confidence upper
- 1388.7199838946353
Original result ↗1,371.66
- source id
- lmarena
- leaderboard name
- LMArena Text Non English
- dimension
- general
- metric
- Arena rating
- rank
- 175
- sample size
- 13538
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1365.8037480307262
- confidence upper
- 1377.51661396778
Original result ↗1,357.849
- source id
- lmarena
- leaderboard name
- LMArena Text Exclude Ties
- dimension
- general
- metric
- Arena rating
- rank
- 175
- sample size
- 16338
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1351.1615430362206
- confidence upper
- 1364.5372725719867
Original result ↗1,398.108
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Mathematical
- dimension
- style
- metric
- Arena rating
- rank
- 176
- sample size
- 1204
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1381.5197073961754
- confidence upper
- 1414.695501030916
Original result ↗1,428.203
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Software And It Services
- dimension
- style
- metric
- Arena rating
- rank
- 177
- sample size
- 7947
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1421.0783564268404
- confidence upper
- 1435.328436257976
Original result ↗1,391.209
- source id
- lmarena
- leaderboard name
- LMArena Text English
- dimension
- general
- metric
- Arena rating
- rank
- 177
- sample size
- 9741
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1384.6615299707469
- confidence upper
- 1397.7562285313036
Original result ↗1,378.551
- source id
- lmarena
- leaderboard name
- LMArena Text Longer Query
- dimension
- general
- metric
- Arena rating
- rank
- 178
- sample size
- 4937
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1370.0232459383553
- confidence upper
- 1387.0785262099357
Original result ↗1,369.56
- source id
- lmarena
- leaderboard name
- LMArena Text Russian
- dimension
- general
- metric
- Arena rating
- rank
- 180
- sample size
- 1562
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1355.2610244342777
- confidence upper
- 1383.8596382931823
Original result ↗1,363.01
- source id
- lmarena
- leaderboard name
- LMArena Text Instruction Following
- dimension
- general
- metric
- Arena rating
- rank
- 180
- sample size
- 5965
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1355.1721752030587
- confidence upper
- 1370.8469072238704
Original result ↗1,315.87
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Korean
- dimension
- style
- metric
- Arena rating
- rank
- 180
- sample size
- 590
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1290.5166058349928
- confidence upper
- 1341.2227653605223
Original result ↗1,378.338
- source id
- lmarena
- leaderboard name
- LMArena Text Multi Turn
- dimension
- general
- metric
- Arena rating
- rank
- 181
- sample size
- 3928
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1368.7944644817944
- confidence upper
- 1387.8812806751585
Original result ↗1,406.914
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Hard Prompts
- dimension
- style
- metric
- Arena rating
- rank
- 186
- sample size
- 10960
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1400.6103537922502
- confidence upper
- 1413.2178863602514
Original result ↗1,399.953
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Medicine And Healthcare
- dimension
- style
- metric
- Arena rating
- rank
- 187
- sample size
- 1325
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1383.4831322972211
- confidence upper
- 1416.4235373819404
Original result ↗1,367.688
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Non English
- dimension
- style
- metric
- Arena rating
- rank
- 187
- sample size
- 13538
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1361.7980767989015
- confidence upper
- 1373.5788559099979
Original result ↗1,416.399
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Hard Prompts English
- dimension
- style
- metric
- Arena rating
- rank
- 188
- sample size
- 4738
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-30B-A3B-Instruct (2507)
- confidence lower
- 1407.649806339666
- confidence upper
- 1425.1487709292358
Original result ↗Published prices
1–5 / 5
$0.10
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
$0.10
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.30
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
$0.09
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing label
- Input tokens (per 1M)
$0.30
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing label
- Output tokens (per 1M)
Provider specifications & access
1–9 / 9
- source model id
- azure-huggingface/qwen--qwen3-30b-a3b-instruct-2507@1
- hosting
- foundry-managed-compute
- license
- apache-2.0
- context length
- 262144
- source model id
- azure-huggingface/qwen--qwen3-30b-a3b-instruct-2507@2
- hosting
- foundry-managed-compute
- license
- apache-2.0
- context length
- 262144
- source model id
- HuggingFace/qwen-qwen3-30b-a3b-instruct-2507@1
- hosting
- foundry-managed-compute
- license
- apache-2.0
- source model id
- HuggingFace/qwen-qwen3-30b-a3b-instruct-2507@2
- hosting
- foundry-managed-compute
- license
- apache-2.0
- source model id
- HuggingFace/qwen-qwen3-30b-a3b-instruct-2507@3
- hosting
- foundry-managed-compute
- license
- apache-2.0
- source model id
- HuggingFace/qwen-qwen3-30b-a3b-instruct-2507@4
- hosting
- foundry-managed-compute
- license
- apache-2.0
- source model id
- publishers/hf-qwen/models/qwen3-30b-a3b-instruct-2507@001
- hosting
- vertex-self-deployed
- source model id
- publishers/qwen/models/qwen3@qwen3-30b-a3b-instruct-2507
- hosting
- vertex-self-deployed
- source model id
- Qwen/Qwen3-30B-A3B-Instruct-2507
- hosting
- siliconflow-hosted
- max output tokens
- 262144
- capabilities
- structuredOutputs
- toolCalling
Safety assessments
1–1 / 1
26 / 100
- source id
- stanfordFMTI
- canonical model id
- qwen/qwen3-30b-a3b-instruct-2507
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- Alibaba
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 26 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–7 / 7
- field
- context_length
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 262144
- normalized value
- 262144
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 262K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2025-06-30
- normalized value
- 2025-06-30
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 235929
- normalized value
- 235929
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 262K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
Hugging Face model card
1–1 / 1
- downloads
- 863158
- likes
- 857
- pipeline tag
- text-generation
- library name
- transformers
- License
- apache-2.0
Explore more models