Thai instruct model
According to the model card, it is an instruct Thai large language model based on Qwen3 4B and described as a 4B instruct decoder-only model on the Qwen3 architecture.
Open Source Model Profile · FILM6912
typhoon2.5-qwen3-4b
typhoon2.5-qwen3-4b is a Qwen3 text-generation model from FILM6912 with about 4.02B parameters. According to the model card, it is a Thai instruct model with function-calling capabilities.
- Publisher
- FILM6912
- Task
- text-generation
- Model type
- qwen3
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
typhoon2.5-qwen3-4b is published by FILM6912 as a text-generation model. The captured configuration identifies Qwen3ForCausalLM with model type qwen3, and Safetensors metadata reports 4,022,468,096 parameters. According to the model card, it is an instruct Thai model based on Qwen3 4B with function-calling capabilities and a claimed 256k context length.
Recorded capabilities
Documented function calling
According to the model card, the model has function-calling capabilities with vLLM tool-calling documentation, a function-tool schema example, and sampling guidance of low temperature with repetition penalty 1.05.
256k context claim
According to the model card, the model has a 256k context length.
Transformers usage path
According to the model card, transformers 4.51.0 or newer is required, with a documented Thai and English text-generation usage example.
Use cases in the source record
- Thai and English instruct text generation using the documented Transformers chat-message workflow.
- Tool-calling experiments using the documented vLLM OpenAI-compatible setup with the hermes parser and the card's function-tool example.
Limitations and unknowns
- No evaluation results were extracted from this record.
- The 256k context length is a publisher model-card claim and was not independently verified.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
Source and provenance
Source: FILM6912/typhoon2.5-qwen3-4b
Captured: Unknown. Processed: 2026-09-07T19:35:39.398982+00:00.
Typhoon2.5-Qwen3-4B : Thai Large Language Model (Instruct) Typhoon2.5-Qwen3-4B is a instruct Thai 🇹🇭 large language model with 4 billion parameters, a 256k context length, and function-calling capabilities. It is based on Qwen3 4B. Performance Model Description Model type : A 4B instruct decoder-only model based on Qwen3 architecture. Requirement : transformers 4.51.0 or newer. Primary Language(s) : Thai 🇹🇭 and English 🇬🇧 Context Length : 256K License : Apache 2.0 License Usage Example This code snippet shows how to use the Typhoon2.5-Qwen3-4B model for Thai or English text generation using the transformers library. It include…
F001F002F003F004F005F006F007F010F011F013F014F015F016F017F018