back

Typhoon 2.1 12B

Gemma

SCB 10X · 11.8B · Dense

Flagship Thai/English bilingual model built on Gemma 3, with a thinking mode

0 downloads 0 likes 2025-05 128K context

Use Cases

chat multilingual reasoning

Quantization Options

Quant Bits VRAM Quality Status
Q2_K 2 4.3 GB low
Q3_K_M 3 5.8 GB moderate
Q4_K_M 4 6.5 GB good
Q5_K_M 5 8.1 GB good
Q6_K 6 9.6 GB excellent
Q8_0 8 12.6 GB excellent
F16 16 24.7 GB lossless

About this model

Typhoon2.1-Gemma3-12B: Thai Large Language Model (Instruct) - Q4_K_M quantized

Typhoon2.1-Gemma3-12B is a instruct Thai 🇹🇭 large language model with 12 billion parameters, and it is based on Gemma3 12B.

By using this model, you agree to the OpenTyphoon Terms and Conditions and acknowledge the Privacy Notice: https://opentyphoon.ai/tac · https://opentyphoon.ai/privacy

Remark: This is text only model.

Run

ollama run scb10x/typhoon2.1-gemma3-12b

Performance

12b model performance