iapp

chinda-qwen3-4b

Chinda Opensource Thai LLM 4B is iApp Technology's cutting-edge Thai language model that brings advanced thinking capabilities to the Thai AI ecosystem. Built on the latest Qwen3-4B architecture, represents our commitment to developing Thai sovereign AI.

1,449 Pulls 1 Tag Updated 1 year ago

openthai-systemone

Thai + English System One decision model (0.8B) for Ollama's /v1/systemone: choice, yes/no and score answers with probabilities, ~20 ms per question. Thai 82.5 vs Nimble 9B 78.3.

0.8b

65 Pulls 5 Tags Updated 6 days ago

openthai2.0-qwen3.8-27b

OpenThai2.0 - Best All-in-One Opensource Thai Knowledge, Document, and Agentic AI

vision tools thinking

26 Pulls 1 Tag Updated 6 days ago

openthai-1.5-7b

The smallest OpenThai model — Thai chat on an ordinary laptop (~8 GB RAM). Fine-tuned on 2M+ Thai instruction pairs; multi-turn, RAG and tool calling.

12 Pulls 2 Tags Updated 6 days ago

openthai-r1-32b

Thai reasoning model that shows its step-by-step thinking — beats DeepSeek R1 70B and Typhoon R1 70B on Thai benchmarks (avg 71.58 vs 63.31/65.42) at half their size. ~24 GB RAM.

11 Pulls 2 Tags Updated 6 days ago

openthai-2.0-legal

Thai legal LLM that cites the exact law name and section (มาตรา). 30B MoE, ~3B active per token — runs in ~24 GB. Best paired with retrieval (RAG). Decision support, not legal advice.

tools thinking

6 Pulls 2 Tags Updated 6 days ago

openthai-1.6-72b

OpenThai's general-purpose flagship — 98.2% Thai language accuracy, strongest of the family at Thai coding. ~48 GB RAM/VRAM.

5 Pulls 2 Tags Updated 6 days ago

iApp Technology Co., Ltd