laya-thai is an open-weight model from Opendream, released under Creative Commons Attribution-NonCommercial 4.0. It has 322M parameters. At 16-bit it needs about 0.8 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Fine-tune of convaiinnovations/laya (subfolder="multilingual") for Thai typed decisions. The model does not write text. One forward pass stamps choice, score, and noul (yes/no) answers and returns a probability for each. The weights in this repo are epoch02.
Runs On
What it takes to serve laya-thai (322M 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 | 0.6 GB | 0.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.3 GB | 0.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x 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, read Oct 1, 2026.
laya-thai on every accelerator the SAVRN Index prices, at every precision
Model Card
Fine-tune of convaiinnovations/laya (subfolder="multilingual") for Thai typed decisions. The model does not write text. One forward pass stamps choice, score, and noul (yes/no) answers and returns a probability for each. The weights in this repo are epoch02. The config is the calibrated one: same weights, softer confidence. A single temperature does not change the chosen label. This release is published by the Hugging Face organization that owns the repo. No individual author is named. The model is a fine-tune, not a new base: Comparison numbers for iapp/OpenThai-SystemOne in the speed table were measured locally from those weights. iApp is not an author of this fine-tune. Route a Thai…
Excerpt from the card by Opendream, licensed cc-by-nc-4.0.
Identity and Version
- Repository
- team-od/laya-thai
- Publisher
- Opendream
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 322M parameters
- Languages
- th, en
- Revision
- 85fe58c9c7638d55b8708d4c7261b64d076db389
- First published
- 2026-09-27
- Last updated
- 2026-09-27
Files and Weights
7 files, 678.2 MB in total. The weights are 1 file totalling 643.8 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 643.8 MB | 9eeea1659bd8 |
| encoder/config.json | Configuration | 1.9 KB | — |
| rl_agent_config.json | Configuration | 895 B | — |
| README.md | Documentation | 10.6 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer/tokenizer.json | Tokenizer | 34.4 MB | 609d8f4c067c |
| tokenizer/tokenizer_config.json | Tokenizer | 623 B | — |
License and Download
- License
- cc-by-nc-4.0
- Access
- Open weights, no gate
- Download size
- 643.8 MB
Released by Opendream through its official repository on Hugging Face. Read the license.
Built From
- Derived from convaiinnovations/laya
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 643.8 MB |
| 16-bit | 0.6 GB |
| 8-bit | 0.3 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About laya-thai
How much GPU memory does laya-thai need?
About 0.8 GB at 16-bit and 0.2 GB at 4-bit: the weights (322M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run laya-thai 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 laya-thai commercially?
Not without separate permission. laya-thai is released under Creative Commons Attribution-NonCommercial 4.0. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder.