Model reference · open weights
openthaigpt1.5 is an open-weight language model from openthaigpt. openthaigpt1.5-7b-instruct (BF16) weighs 15.2 GB; the smallest configuration that runs it is 2× RTX 3060 12 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the openthaigpt/openthaigpt1.5-7b-instruct model card, 2026-10-01
What it is
| Released by | openthaigpt |
|---|---|
| Released | 2024-09-30 |
| Parameters | 7.6B |
| VRAM | 15.2 GB for the weights |
What it runs on
| Card | Requests at once | Context max | Memory | |
|---|---|---|---|---|
| 8K each | 32K each | |||
| RTX 3060 12 GB … RTX 4060 Ti 16 GB 2 smaller cards | ||||
| RTX 3090 24 GB | 15 | 3 | all 32K | 23.4 GB |
| RTX 4090 24 GB | 15 | 3 | all 32K | 23.4 GB |
| RTX 5090 32 GB | 32 | 8 | all 32K | 31.0 GB |
| L40S 48 GB | 59 | 14 | all 32K | 44.0 GB |
| A100 80 GB | 132 | 33 | all 32K | 78.2 GB |
| H100 80 GB | 132 | 33 | all 32K | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | 165 | 41 | all 32K | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | 194 | 48 | all 32K | 107 GB |
| H200 141 GB | 259 | 64 | all 32K | 138 GB |
| B200 180 GB | 341 | 85 | all 32K | 176 GB |
| 2× RTX 3060 12 GB split by layers (llama.cpp) | 14 | 3 | all 32K | 11.6 GB a card |
| 2× RTX 4060 Ti 16 GB split by layers (llama.cpp) | 30 | 7 | all 32K | 15.4 GB a card |
| Requests at once | 8K tokens each | 32K tokens each |
|---|---|---|
| 1 | 16.4 GB | 17.8 GB |
| 5 | 18.3 GB | 25.3 GB |
| 8 | 19.7 GB | 31.0 GB |
| 16 | 23.5 GB | 46.0 GB |
| 32 | 31.0 GB | 76.1 GB |
| 64 | 46.0 GB | 136 GB |
One card, with vLLM's small-card settings.
From the model card
🇹🇭 OpenThaiGPT 7b Version 1.5 is an advanced 7-billion-parameter Thai language chat model based on Qwen v2.5 released on September 30, 2024. It has been specifically fine-tuned on over 2,000,000 Thai instruction pairs and is capable of answering Thai-specific domain questions.
https://demo72b.aieat.or.th/
https://github.com/OpenThaiGPT/openthaigpt1.5_api_examples
📢 OpenThaiGPT is now OpenThai
The project was renamed in July 2026. Released models keep their original names, and this repository path is unchanged and permanent. → openthai.aieat.or.th
| Need | Model |
|---|---|
| ⚖️ Thai law, statute citation, legal RAG | OpenThai 2.0 Legal 30B-A3B ← newest |
| 🧠 Reasoning, maths, logic, code | OpenThaiGPT R1 32B |
| 💬 General Thai chat and coding | OpenThaiGPT 1.6 72B |
| 💻 Limited GPU | OpenThaiGPT 1.5 7B |
ollama run openthai/openthai-1.5-7b
Official GGUF quants (Q4_K_M / Q5_K_M / Q8_0): openthaigpt/openthaigpt1.5-7b-instruct-GGUF — runs in ~8 GB RAM, no GPU needed. Step-by-step guide: openthai.aieat.or.th/ollama
** Please take a look at openthaigpt/openthaigpt1.5-7b-instruct for this model's evaluation result.
| Exam names | scb10x/llama-3-typhoon-v1.5x-8b-instruct | meta-llama/Llama-3.1-7B-Instruct | Qwen/Qwen2.5-7B-Instruct_stat | openthaigpt/openthaigpt1.5-7b |
|---|---|---|---|---|
| 01_a_level | 46.67% | 47.50% | 58.33% | 60.00% |
| 02_tgat | 32.00% | 36.00% | 32.00% | 36.00% |
| 03_tpat1 | 52.50% | 55.00% | 57.50% | 57.50% |
| 04_investment_consult | 56.00% | 48.00% | 68.00% | 76.00% |
| 05_facebook_beleble_th_200 | 78.00% | 73.00% | 79.00% | 81.00% |
| 06_xcopa_th_200 | 79.50% | 69.00% | 80.50% | 81.00% |
| 07_xnli2.0_th_200 | 56.50% | 55.00% | 53.00% | 54.50% |
| 08_onet_m3_thai | 48.00% | 32.00% | 72.00% | 64.00% |
| 09_onet_m3_social | 75.00% | 50.00% | 90.00% | 80.00% |
| 10_onet_m3_math | 25.00% | 18.75% | 31.25% | 31.25% |
| 11_onet_m3_science | 46.15% | 42.31% | 46.15% | 46.15% |
| 12_onet_m3_english | 70.00% | 76.67% | 86.67% | 83.33% |
| 13_onet_m6_thai | 47.69% | 29.23% | 46.15% | 53.85% |
| 14_onet_m6_math | 29.41% | 17.65% | 29.41% | 29.41% |
| 15_onet_m6_social | 50.91% | 43.64% | 56.36% | 58.18% |
| 16_onet_m6_science | 42.86% | 32.14% | 57.14% | 57.14% |
| 17_onet_m6_english | 65.38% | 71.15% |
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
Benchmarks
As published on the model card: the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| text-generation | ThaiExam | Thai Exam(Acc) | 52.040 |
| text-generation | M3Exam | M3Exam(Acc) | 54.010 |