OpenThai SystemOne needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.5 GB (Q4_0) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
OpenThai SystemOne – a Thai+English decision model without text generation
OpenThai SystemOne is a Qwen3.5‑0.8B text tower with a 256‑slot decision head. It returns calibrated probabilities for up to 255 options in a single forward pass. The model is trained on Thai and English decision tasks and does not generate text.
Good at
- Decision making over many options
- Calibrated probability outputs
- Tool and action selection
Limits
- No text generation
- No vision support
- Requires 8k context for memory estimates
Best for
- Ticket routing
- Moderation and intent detection
- RAG relevance judging
Who it’s for. Developers needing a fast, non‑generative decision engine for Thai and English data. It is suitable for integration with TypeSafe‑compatible APIs and for use in LLM‑output verification workflows.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q6_K | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 1.7 GB | Fits | Get file → | |
| BF16 | 1.5 GB | 2.4 GB | Fits | Get file → | |
| F16 | 1.5 GB | 2.4 GB | Fits | Get file → |
For 8 GB VRAM, Q4_0 or Q4_K_M (0.5 GB or 0.53 GB) are recommended, each using about 1.4 GB at 8k context. If more memory is available, Q5_K_M or Q6_K (0.58 GB/0.63 GB) use about 1.5 GB. Larger BF16 or F16 (1.52 GB) need roughly 2.4 GB.
What GPU do you need for OpenThai SystemOne?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is BF16 (1.5 GB file, about 2.4 GB in use).
Which OpenThai SystemOne quant should you choose?
Q4_K_M is the usual starting point for OpenThai SystemOne: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.8 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q4_0 at 0.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about OpenThai SystemOne
How much VRAM does OpenThai SystemOne need?
About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run OpenThai SystemOne on an 8 GB GPU?
Yes, with BF16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of OpenThai SystemOne GGUF?
It depends on the quant: Q4_0 is 0.5 GB, Q4_K_M is 0.5 GB, Q5_K_M is 0.6 GB, Q6_K is 0.6 GB, Q8_0 is 0.8 GB, BF16 is 1.5 GB and 1 more.
What context length does OpenThai SystemOne support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download OpenThai SystemOne GGUF?
The files are on Hugging Face in the iapp/OpenThai-SystemOne-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does OpenThai SystemOne use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run OpenThai SystemOne on 8 GB VRAM?
Yes, the Q4_0 or Q4_K_M quantizations fit within 8 GB VRAM, using about 1.4 GB at 8k context.
Does this model support vision input?
No, the vision encoder has been removed; the model only processes text or JSON states.
What license applies to this model?
The model is released under the apache-2.0 license.