reasoning
QwQ-32B-Preview
QwQ-32B-Preview is an experimental Qwen research model focused on reasoning, strong in math and coding, fine-tuned from Qwen2.5-32B-Instruct.
Levelmodel
Classreasoning
Parameters32.5B
Context32,768
Released28 Nov 2024
Opennessopen weights permissive
Runs onnot in the notes
Statuspreview
Benchmark Results
vendor-reported
vendor-reported
50
050100
Score in %. Higher is better.
GPQAknowledge and reasoning
vendor-reported
65.2
050100
Score in %. Higher is better.
LiveCodeBenchcoding
vendor-reported
50
050100
Score in %. Higher is better.
MATH500math
vendor-reported
90.6
050100
Score in %. Higher is better.
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
finetune
Qwen2.5-32B-Instruct is the parent (finetune)high confidenceHugging Face base_modelWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.
R&D Topics
Identity
- Developer
- Alibaba (Qwen)
- Family
- Qwen
- Released
- 28 Nov 2024 sourcesannouncement page
- Weights published
- 27 Nov 2024
- Record checked
- 11 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer Causal transformer with RoPE, SwiGLU, RMSNorm and attention QKV bias; 64 layers; GQA 40 Q and 8 KV heads
- Total parameters
- 32.5B sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- 31.0B non-embedding
- Context length
- 32,768 tokens
- Input
- text
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- Apache License 2.0 sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- Card language tag: English; card warns of language mixing and code-switching
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Industry Use Cases
No industry use case links this model.
Links
DeveloperAlibaba (Qwen)big tech, China
Alibaba (Qwen)big tech, ChinaModelQwQ-32B-PreviewAlibaba (Qwen), reasoning
QwQ-32B-PreviewAlibaba (Qwen), reasoningR&D TopicsReasoning via Large-Scale RL
Use CasesChinese Medical LLMsHealthcareUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs Itnone recordedDeployments of these use cases; none names this model.
Organisations 1
Sources
- qwenlm.github.io/blog/qwq-32b-preview https://qwenlm.github.io/blog/qwq-32b-preview/
- huggingface.co/Qwen/QwQ-32B-Preview https://huggingface.co/Qwen/QwQ-32B-Preview
- huggingface.co/api/models/Qwen/QwQ-32B-Preview https://huggingface.co/api/models/Qwen/QwQ-32B-Preview
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "QwQ-32B-Preview", https://aurion.semai.id/models/alibaba-qwq-32b-preview/, records of October 2026.