Qwen-SEA-LION-v4-32B-IT
Qwen-SEA-LION-v4-32B-IT is AI Singapore's instruction-tuned model built on Qwen3-32B, continued-pretrained on about 100 billion tokens of SEA-Pile v2 covering Burmese, Indonesian, Malay, Filipino, Tamil, Thai and Vietnamese and post-trained on some 8 million QA pairs for instruction following and multi-turn chat, with an optional thinking mode.
text → text · made by aisingapore
$0.25→$0.5per Mtok in / out
Hugging Face Inference Providers
Sold by 1 way
| Seller | Lane | Rate |
|---|---|---|
| Hugging Face Inference Providers aggregator | publicai | $0.25per Mtok in$0.5per Mtok outrouter.huggingface.co · read 2026-08-25 |
About
Qwen-SEA-LION-v4-32B-IT — a text model from aisingapore.
It takes text and returns text, with a context window of 32,768 tokens. The catalogue files it under chat.
Every current figure
- Maker
- aisingapore
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 32,768 tokens
- Parameters
- 32 billion · read from its own name
- Licence
- not read
Known as 1 name
aisingapore/Qwen-SEA-LION-v4-32B-IT