LLM
Qwen-SEA-LION-v4.5-27B-IT
AI Singapore's 27B Southeast Asian model post-trained on Qwen3.6-27B by logit distillation and merging on SEA-Instruct-2602.
Levelmodel
ClassLLM
Parameters27B
Contextnot in the notes
Released19 May 2026
Opennessopen weights permissive
Runs onconsumer GPU
Statusactive
Benchmark Results
maintainer-run
SEA-HELMSoutheast Asian and Indonesian
maintainer-run
76.51 95% CI [-1.23, +1.23]
04080
Score in score. Higher is better.
rank 4, SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps
maintainer-run
73.24 95% CI [-0.56, +0.57]
04080
Score in score. Higher is better.
rank 4, SEA-HELM SEA average, open-weight models
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
distillfinetune
Qwen3.5-397B-A17B is the parent (distill)high confidencemodel cardQwen3.6-27B is the parent (distill)high confidencemodel cardQwen3.6-27B is the parent (finetune)high confidencemodel cardWhere 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.
Industry Use Cases
Public Sector
Indonesian and regional-language LLMsR&D Topics
Runtimes
Identity
- Developer
- AI Singapore
- Family
- SEA-LION
- Released
- 19 May 2026 sourcesregistry date
- Weights published
- –
- Record checked
- 10 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
- not in the notes
- Total parameters
- 27B sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- 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
- MIT License sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- consumer GPU
- Footprint
- OpenVINO 4- and 8-bit variants (v4-32B)
- Runtimes
- OpenVINO
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
- measured on a benchmark
- SEA-HELM Indonesian leaderboard (ID aggregate, first score column of the Indonesian Competency and Task Scores table): 76.51 (95% CI -1.23 to +1.23), run by AI Singapore (SEA-HELM leaderboard maintainer) leaderboard.sea-lion.ai
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- English, Burmese, Indonesian, Filipino, Malay, Tamil, Thai, Vietnamese
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Links
DeveloperAI Singaporenational lab, Singapore
AI Singaporenational lab, SingaporeModelQwen-SEA-LION-v4.5-27B-ITAI Singapore, LLM
Qwen-SEA-LION-v4.5-27B-ITAI Singapore, LLMR&D TopicsDistillation of Frontier Models into Smaller OnesLow-Resource and Regional Language ResourcesRegional or National Foundation Model Training (Continued Pretraining at 7B to 70B)
Who Runs Itnone recordedDeployments of these use cases; none names this model.
Models 3
Organisations 1
R&D topics 3
Regional or National Foundation Model Training (Continued Pretraining at 7B to 70B)Pretraining or continued pretraining a mid-size model to serve a national or regional lan…produced byLow-Resource and Regional Language ResourcesDatasets, benchmarks and adaptation for under-served languages.produced byDistillation of Frontier Models into Smaller OnesTransferring capability from a large teacher model to a smaller one.used by
Sources
- aisingapore/Qwen-SEA-LION-v4.5-27B-IT , Hugging Face huggingface.co https://huggingface.co/aisingapore/Qwen-SEA-LION-v4.5-27B-IT
- SEA-HELM Leaderboard leaderboard.sea-lion.ai/detailed/SEA https://leaderboard.sea-lion.ai/detailed/SEA
- SEA-HELM Leaderboard leaderboard.sea-lion.ai/detailed/ID https://leaderboard.sea-lion.ai/detailed/ID
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Qwen-SEA-LION-v4.5-27B-IT", https://aurion.semai.id/models/ai-singapore-qwen-sea-lion-v4-5-27b-it/, records of October 2026.