iapp/openthai2.0-legal-thaillm-nemotron-3-nano-30b-a3b

Text Generation • 32B • Updated Aug 13 • 153 • 6

Note ⚖️ Thai law, statute citation, legal RAG. 30B MoE, ~3B active — runs on one 24 GB GPU.

openthaigpt/openthaigpt-r1-32b-instruct

Text Generation • 33B • Updated Jul 27 • 190 • 8

Note 🧠 Reasoning, maths, logic, code in Thai. Beats 70B models at half the size.

openthaigpt/openthaigpt-1.6-72b-instruct

Text Generation • 73B • Updated Jul 27 • 85 • 5

Note 💬 General Thai chat and coding. 98.2% Thai language accuracy.

openthaigpt/openthaigpt1.5-7b-instruct

Text Generation • 8B • Updated Jul 27 • 1.67k • • 17

Note 💻 Smallest option — for limited GPU budgets.