# OpenThai-SystemOne by iApp Technology: Open-Weight Model Source: https://savrn.com/models/openthai-systemone Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve OpenThai-SystemOne (753M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 1.5 GB | 1.8 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.8 GB | 0.9 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.4 GB | 0.5 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 7, 2026. [OpenThai-SystemOne on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/openthai-systemone/gpus) ## Model Card By iApp Technology, published under apache-2.0, revision dc67b0295ab7. An open Thai + English "System One" decision model. It does not generate text. Given a state (any text or JSON) and typed questions, it returns calibrated probabilities over the options in one forward pass: | Question | You give | You get | | --- | --- | --- | | choice | instructions + up to 255 options (name → description or null) | choice, probabilities, confidence | | score | instructions + 2–10 ordered level descriptions | score (probability-weighted, fractional), probabilities, confidence | | noul | a yes/no question | noul = p(yes) | The request/response contract mirrors TypeSafe's POST /v1/systemone so code written for the TypeSafe SDK can be pointed at this model unchanged. Typical uses: ticket routing, moderation, intent detection, RAG relevance judging, LLM-output verification, and computer-use / browser-agent action selection (which element to click, which tool to call). ### How it works [Read the full model card (3,047 words)](https://savrn.com/models/openthai-systemone/card) ## Configuration Architecture OpenThaiSystemOneForDecision Context length (tokens) 262,144 Layers 24 Hidden size 1,024 Feed-forward size 3,584 Attention heads 8 Key/value heads 2 Head dimension 256 Vocabulary size 248,339 Model type openthai_systemone ## Identity and Version Repository iapp/OpenThai-SystemOne Publisher iApp Technology Task Zero-shot classification Modality Text Library Not stated by the source Parameters 753M parameters Languages th, en Revision dc67b0295ab7ac94b05d27187150d9a4b5784554 First published 2026-09-20 Last updated 2026-10-01 ## Files and Weights 16 files, 1.5 GB in total. The weights are 1 file totalling 1.5 GB in safetensors. Weights1 file · 1.5 GB Configuration5 files · 28.5 KB Tokenizer2 files · 20.0 MB Documentation1 file · 25.8 KB Other6 files · 14.8 MB Repository1 file · 1.8 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 1.5 GB | e5bf18fbd975 | | config.json | Configuration | 2.7 KB | — | | configuration.py | Configuration | 1.4 KB | — | | formatting.py | Configuration | 10.8 KB | — | | modeling.py | Configuration | 9.3 KB | — | | types.py | Configuration | 4.3 KB | — | | README.md | Documentation | 25.8 KB | — | | assets/doom_10s.gif | Other | 9.7 MB | 515677e3a007 | | assets/openthai-systemone-launch-en.png | Other | 4.4 MB | 2eb34c3af49e | | assets/openthai-systemone-launch.jpg | Other | 227.7 KB | 3d28ddfc09d5 | | assets/siamai-logo.png | Other | 45.1 KB | — | | assets/thai-showcase.png | Other | 393.9 KB | c5eaca95325d | | chat_template.jinja | Other | 7.8 KB | — | | .gitattributes | Repository | 1.8 KB | — | | tokenizer.json | Tokenizer | 20.0 MB | d3400f1532d5 | | tokenizer_config.json | Tokenizer | 1.1 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 1.5 GB [Download from iApp Technology](https://huggingface.co/iapp/OpenThai-SystemOne) Released by iApp Technology through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from Qwen/Qwen3.5-0.8B-Base ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 1.5 GB | | 16-bit | 1.5 GB | | 8-bit | 0.8 GB | | 4-bit | 0.4 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Built on This Model - Derived from[OpenThai-SystemOne-Ollama](https://savrn.com/models/openthai-systemone-ollama) ## Questions About OpenThai-SystemOne ### How much GPU memory does OpenThai-SystemOne need? About 1.8 GB at 16-bit and 0.5 GB at 4-bit: the weights (753M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run OpenThai-SystemOne on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use OpenThai-SystemOne commercially? Yes. OpenThai-SystemOne is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is OpenThai-SystemOne's context length? 262,144 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Zero-shot classification ### [Vela-2.0-0.8B](https://savrn.com/models/vela-2-0-0-8b) [vLLM Semantic Router](https://savrn.com/model-publishers/vllm-sr) Open Foundation Routing Models Routing decisions. Safety checks. Precise text spans. The compact hybrid member of Vela 2.0: a 756M-parameter model for multilingual routing, safety checks and span-level decisions through one interface. Define options, labels and rubrics at request time. Ask multiple named questions about a request, context and answer, and receive structured decisions with the text spans that support your workflow. 1. Compact deployment. About 3 GB of GPU memory for FP32 parameters, with a 16,384-token input limit. 2. Routing and safety together. Use one request for routing, prompt-attack checks, PII and unsupported-claim detection. 3. Decisions at span resolution. Return… Open weights apache-2.0 755M parameters [View model](https://savrn.com/models/vela-2-0-0-8b) Model · Zero-shot classification ### [LLM2CLIP-Openai-L-14-336](https://savrn.com/models/llm2clip-openai-l-14-336) [Microsoft](https://savrn.com/model-publishers/microsoft) Weiquan Huang 1, Aoqi Wu 1, Yifan Yang 2†, Xufang Luo 2, Yuqing Yang 2, Liang Hu 1, Qi Dai 2, Xiyang Dai 2, Dongdong Chen 2, Chong Luo 2, Lili Qiu 2 In this paper, we propose LLM2CLIP, a novel approach that embraces the power of LLMs to unlock CLIP’s potential. By fine-tuning the LLM in the caption space with contrastive learning, we extract its textual capabilities into the output embeddings, significantly improving the output layer’s textual discriminability. We then design an efficient training process where the fine-tuned LLM acts as a powerful teacher for CLIP’s visual encoder. Thanks to the LLM’s presence, we can now incorporate longer and more complex captions without being… Open weights apache-2.0 579M parameters [View model](https://savrn.com/models/llm2clip-openai-l-14-336) Model · Zero-shot classification ### [bge-m3-zeroshot-v2.0](https://savrn.com/models/bge-m3-zeroshot-v2-0) [Moritz Borrett-Laurer (formerly Laurer)](https://savrn.com/model-publishers/moritzlaurer) Models in this series are designed for efficient zeroshot classification with the Hugging Face pipeline. These models can do classification without training data and run on both GPUs and CPUs. An overview of the latest zeroshot classifiers is available in my Zeroshot Classifier Collection. The main update of this zeroshot-v2.0 series of models is that several models are trained on fully commercially-friendly data for users with strict license requirements. These models can do one universal classification task: determine whether a hypothesis is "true" or "not true" given a text (entailment vs. notentailment). This task format is based on the Natural Language Inference task (NLI). The task is… Open weights mit 568M parameters 8,194 tokens transformers [View model](https://savrn.com/models/bge-m3-zeroshot-v2-0) Model · Zero-shot classification ### [xlm-roberta-large-xnli](https://savrn.com/models/xlm-roberta-large-xnli) [Joe Davison](https://savrn.com/model-publishers/joeddav) This model takes xlm-roberta-large and fine-tunes it on a combination of NLI data in 15 languages. It is intended to be used for zero-shot text classification, such as with the Hugging Face ZeroShotClassificationPipeline. This model is intended to be used for zero-shot text classification, especially in languages other than English. It is fine-tuned on XNLI, which is a multilingual NLI dataset. The model can therefore be used with any of the languages in the XNLI corpus: Since the base model was pre-trained trained on 100 different languages, the model has shown some effectiveness in languages beyond those listed above as well. See the full list of pre-trained languages in appendix A of the… Open weights mit 561M parameters 514 tokens transformers [View model](https://savrn.com/models/xlm-roberta-large-xnli) Model · Zero-shot classification ### [DeBERTa-v3-large-mnli-fever-anli-ling-wanli](https://savrn.com/models/deberta-v3-large-mnli-fever-anli-ling-wanli) [Moritz Borrett-Laurer (formerly Laurer)](https://savrn.com/model-publishers/moritzlaurer) This model was fine-tuned on the MultiNLI, Fever-NLI, Adversarial-NLI (ANLI), LingNLI and WANLI datasets, which comprise 885 242 NLI hypothesis-premise pairs. This model is the best performing NLI model on the Hugging Face Hub as of 06.06.22 and can be used for zero-shot classification. It significantly outperforms all other large models on the ANLI benchmark. The foundation model is DeBERTa-v3-large from Microsoft. DeBERTa-v3 combines several recent innovations compared to classical Masked Language Models like BERT, RoBERTa etc., see the paper DeBERTa-v3-large-mnli-fever-anli-ling-wanli was trained on the MultiNLI, Fever-NLI, Adversarial-NLI (ANLI), LingNLI and WANLI datasets, which… Open weights mit 435M parameters 512 tokens transformers [View model](https://savrn.com/models/deberta-v3-large-mnli-fever-anli-ling-wanli) Model · Zero-shot classification ### [nli-deberta-v3-large](https://savrn.com/models/nli-deberta-v3-large) [Sentence Transformers - Cross-Encoders](https://savrn.com/model-publishers/cross-encoder) This model was trained using SentenceTransformers Cross-Encoder class. This model is based on microsoft/deberta-v3-large The model was trained on the SNLI and MultiNLI datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral. For futher evaluation results, see SBERT.net - Pretrained Cross-Encoder. Pre-trained models can be used like this: You can use the model also directly with Transformers library (without SentenceTransformers library): This model can also be used for zero-shot-classification Open weights apache-2.0 435M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/nli-deberta-v3-large) ## iApp Technology [All models and datasets](https://savrn.com/model-publishers/iapp) ## Versions - [dc67b0295ab7](https://savrn.com/models/openthai-systemone/versions/dc67b0295ab7) · current 2026-10-01 - [6f5fee848c8d](https://savrn.com/models/openthai-systemone/versions/6f5fee848c8d) 2026-09-21 ## Explore More - [All zero-shot classification models](https://savrn.com/models/tasks/zero-shot-classification) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-01. - [Hugging Face record](https://huggingface.co/iapp/OpenThai-SystemOne) - [How the hub is built](https://savrn.com/model-hub/methodology)