openthaigpt1.5 7b instruct needs about 5.7 GB of memory at its main file (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 3.8 GB to 15.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
OpenThaiGPT 7b 1.5 Instruct – Thai language chat model
OpenThaiGPT 7b 1.5 Instruct is a 7‑billion‑parameter Thai language LLM based on Qwen v2.5. It supports up to 32,768 context tokens and is fine‑tuned on over 2,000,000 Thai instruction pairs.
Good at
- Thai‑specific domain questions
- Multi‑turn conversation
- Tool calling support
Limits
- No vision support
- Requires 8 GB RAM for Q4_K_M quant
- No GPU needed for GGUF
Best for
- Thai language chatbots
- RAG‑enabled applications
- Developer API demos
Who it’s for. Developers building Thai‑language applications and researchers needing a large Thai LLM. It is suitable for local deployment via llama.cpp or ollama.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 3.8 GB | 4.8 GB | Fits | Get file → | |
| — | 4.7 GB | 5.7 GB | Fits | Get file → | |
| F16 | 15.2 GB | 16.2 GB | Too big | Get file → |
For 8 GB RAM, use the Q4_K_M or Q5_K_M quant from the GGUF repo. The unknown quant file is 3.81 GB and needs ~4.8 GB RAM at 8 k context. The F16 quant is 15.24 GB and needs ~16.2 GB RAM.
What GPU do you need for openthaigpt1.5 7b instruct?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is the main file (4.7 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (4.7 GB file, about 5.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (4.7 GB file, about 5.7 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (4.7 GB file, about 5.7 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (15.2 GB file, about 16.2 GB in use).
Which openthaigpt1.5 7b instruct quant should you choose?
If memory is tight, the smallest file is the first one in the table at 3.8 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about openthaigpt1.5 7b instruct
How much VRAM does openthaigpt1.5 7b instruct need?
About 5.7 GB at its main file with an 8K context window. That is the 4.7 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 openthaigpt1.5 7b instruct on an 8 GB GPU?
Yes, with the smaller files: the 4.7 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of openthaigpt1.5 7b instruct GGUF?
It depends on the quant: file is 3.8 GB, file is 4.7 GB, F16 is 15.2 GB.
What context length does openthaigpt1.5 7b instruct support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download openthaigpt1.5 7b instruct GGUF?
The files are on Hugging Face in the openthaigpt/openthaigpt1.5-7b-instruct repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does openthaigpt1.5 7b instruct use?
Hugging Face lists the license as other. 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 this model on 8 GB VRAM?
Yes, the Q4_K_M or Q5_K_M quant runs in ~8 GB RAM and does not require a GPU.
Does it support vision tasks?
No, the model has no vision capability.
What context length does it support?
It can process up to 32,768 tokens of input and generate up to 8,192 tokens.