{"slug": "typhoon-vs-openthai-vs-pathumma-three-thai-llms-worth-knowing", "title": "Typhoon vs OpenThai vs Pathumma: Three Thai LLMs Worth Knowing", "summary": "Three Thai open-weight LLM projects — SCB 10X's Typhoon, the Thai AI Entrepreneur Association's OpenThai, and VISTEC's Pathumma — offer locally runnable, commercially usable alternatives to foreign models, each differentiated by breadth, licensing, and cultural context. Typhoon reports 30 million API calls, 2.6 million downloads, and 13,000 unique users, while OpenThai 2.0 ships under Apache 2.0 at 27 billion parameters with a 30-billion-parameter legal mixture-of-experts variant that activates 3 billion parameters per token. The projects' benchmarks are self-reported, and no independent evaluation compares all three on the same test set.", "body_md": "*By Nokka | September 11, 2026*\n\n*This article was written by AI (deepseek-v4.1-flash) through Hermes Agent, reviewed and edited by Nokka.*\n\nThe first question Thai users ask when starting with AI is often \"does this need a paid API?\" The conversation usually ends with a foreign subscription. The other answer is that Thai teams build open-weight models you can download free and use commercially.\n\nThree projects matter today. Each is strong in a different place, and picking wrong means wasted setup time.\n\nTyphoon is a project from SCB 10X, positioning itself as a frontier AI research lab in Thailand [1].\n\nThe numbers they publish: 30 million API calls, 2.6 million downloads, and 13,000 unique users [1].\n\nWhat separates Typhoon from the other two is breadth. It is not just a chat model. There are reasoning models, speech recognition models, document reading models, and Thai-English translation models [1].\n\nThe most interesting recent work is Typhoon Isan ASR, which recognizes Isan speech. Almost nobody else works on this, because regional dialects are something foreign models skip entirely [1].\n\nOpenThai (formerly OpenThaiGPT) is run by the Thai AI Entrepreneur Association with iApp Technology and a volunteer community [2].\n\nThe clearest differentiator is licensing. The flagship models use Apache 2.0, allowing commercial use without asking permission and without API fees [2].\n\nThe current flagship is OpenThai 2.0 at 27 billion parameters. It reads images, reads Thai handwriting, and handles agent-style tool calling better than the base model it was adapted from [2].\n\nThere is a specialized variant worth noting: OpenThai 2.0 Legal at 30 billion parameters in a mixture-of-experts layout, activating only 3 billion per token, so it runs on a 24 GB GPU. Its standout is recalling legal text from memory and answering with the law name and section number in a format you can feed into other systems [2].\n\nPathumma is developed by a Thai research team at VISTEC, positioned as an open model addressing the rigidity of closed models [3].\n\nWhat differs from the first two is the focus on cultural and Thai contextual understanding, not just grammatical correctness. This is the recurring problem when foreign models read Thai text with social nuance.\n\n|  | Typhoon | OpenThai | Pathumma | \n|---|---|---|---|\n| Owner | SCB 10X | AIEAT + iApp | VISTEC research team | \n| License | Open | Apache 2.0 | Open | \n| Main strength | Broad portfolio (speech/docs/translation) | Thai documents + Thai law | Thai cultural understanding | \n| Runs locally | Yes | Yes (Ollama/LM Studio) | Yes | \n| Regional dialects | Yes (Isan) | No | No | \n| Best for | Teams needing many capabilities | Legal and document work | Language and culture research | \n\n**One** All three are far smaller than frontier foreign models. Against GPT-6 or Claude Opus, multi-step reasoning is still behind. Where they win is Thai-specific work and cost.\n\n**Two** \"Open\" does not mean the same thing across projects. Read the license before commercial use. OpenThai states Apache 2.0 clearly, but check the others carefully.\n\n**Three** Running locally needs adequate hardware. Models at 27 billion parameters and up require substantial GPU or RAM. On a small machine, start with a 7B variant.\n\n**Four** All benchmark numbers come from the projects themselves. There is no independent evaluation comparing all three on the same test set yet. Try them on your own actual work before deciding.\n\nI write Thai content with AI daily, and I keep hitting a problem foreign models handle poorly: phrasing translated straight from English. Grammatically correct sentences nobody actually says.\n\nWhat especially interests me is Typhoon Isan ASR, because frontier labs skip regional speech work for business reasons. Little data, poor return. A Thai team doing it anyway is worth more than any download count.\n\nThe honest counterweight is development speed. Thai projects have much smaller teams, so update cycles are longer. Competing with vendors shipping new models monthly is structurally unfavorable.\n\nMy advice: use Thai models for what they genuinely win, Thai documents, Thai law, Thai speech. For maximum capability work, foreign models remain the tool. That is not a defeat. Knowing where you win is basic to working well.\n\nIf you want to start without installing anything, both OpenThai and Typhoon have free web playgrounds [1][2].\n\n[1] SCB 10X, \"Typhoon — Thailand's Frontier AI Research Lab\" (accessed Sep 11, 2026), [https://opentyphoon.ai/](https://opentyphoon.ai/)\n\n[2] AIEAT & iApp Technology, \"OpenThai — Open Thai Language Models\" (accessed Sep 11, 2026), [https://openthai.aieat.or.th/](https://openthai.aieat.or.th/)\n\n[3] Thai NLP Community, \"Thai large language models benchmarks for cultural and core capabilities\" (2026), [https://www.facebook.com/groups/thainlp/posts/2180375852343893/](https://www.facebook.com/groups/thainlp/posts/2180375852343893/)", "url": "https://wpnews.pro/news/typhoon-vs-openthai-vs-pathumma-three-thai-llms-worth-knowing", "canonical_source": "https://dev.to/sarantoon/typhoon-vs-openthai-vs-pathumma-three-thai-llms-worth-knowing-3g8", "published_at": "2026-09-12 07:10:53+00:00", "updated_at": "2026-09-12 07:26:28.971792+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "natural-language-processing", "ai-products", "ai-startups"], "entities": ["Typhoon", "SCB 10X", "OpenThai", "Thai AI Entrepreneur Association", "iApp Technology", "Pathumma", "VISTEC", "Typhoon Isan ASR"], "alternates": {"html": "https://wpnews.pro/news/typhoon-vs-openthai-vs-pathumma-three-thai-llms-worth-knowing", "markdown": "https://wpnews.pro/news/typhoon-vs-openthai-vs-pathumma-three-thai-llms-worth-knowing.md", "text": "https://wpnews.pro/news/typhoon-vs-openthai-vs-pathumma-three-thai-llms-worth-knowing.txt", "jsonld": "https://wpnews.pro/news/typhoon-vs-openthai-vs-pathumma-three-thai-llms-worth-knowing.jsonld"}}