Thai Research Gemma 3 27b It needs about 22.0 GB of memory at Q4_K_M (a 17.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 23 quants, from 6.7 GB (IQ1_S) to 23.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.
Thai Research Gemma 3 27b It – a Thai‑focused Gemma 3 model
Thai Research Gemma 3 27b It is a fine‑tuned Gemma 3 27B model specialized for Thai. It was trained on 8 billion Thai tokens and instruction fine‑tuned on 3 052 736 Thai QA pairs. The model supports a 131 072 token context and generates up to 8192 tokens.
Good at
- Thai language instruction following
- Thai text generation
- Thai summarization
Limits
- No vision support
- Large VRAM requirement
- License: gemma
Best for
- Thai content creation
- Thai QA systems
- Thai conversational agents
Who it’s for. Developers building Thai‑centric language applications. Researchers needing a Thai‑trained large language model. Teams that require instruction‑fine‑tuned Thai text generation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 6.7 GB | 11.4 GB | Too big | Get file → | |
| IQ1_M | 7.3 GB | 11.9 GB | Too big | Get file → | |
| IQ2_XXS | 8.1 GB | 12.8 GB | Too big | Get file → | |
| IQ2_XS | 8.9 GB | 13.6 GB | Too big | Get file → | |
| IQ2_S | 9.4 GB | 14.0 GB | Too big | Get file → | |
| IQ2_M | 10.1 GB | 14.8 GB | Too big | Get file → | |
| Q2_K_S | 10.2 GB | 14.9 GB | Too big | Get file → | |
| Q2_K | 11.0 GB | 15.6 GB | Too big | Get file → | |
| IQ3_XXS | 11.3 GB | 16.0 GB | Too big | Get file → | |
| IQ3_XS | 12.2 GB | 16.8 GB | Too big | Get file → | |
| IQ3_S | 12.8 GB | 17.4 GB | Too big | Get file → | |
| Q3_K_S | 12.8 GB | 17.4 GB | Too big | Get file → | |
| IQ3_M | 13.2 GB | 17.8 GB | Too big | Get file → | |
| Q3_K_M | 14.0 GB | 18.7 GB | Too big | Get file → | |
| Q3_K_L | 15.1 GB | 19.8 GB | Too big | Get file → | |
| IQ4_XS | 15.5 GB | 20.2 GB | Too big | Get file → | |
| Q4_0 | 16.4 GB | 21.1 GB | Too big | Get file → | |
| Q4_K_S | 16.5 GB | 21.1 GB | Too big | Get file → | |
| Q4_K_M | 17.3 GB | 22.0 GB | Too big | Get file → | |
| Q4_1 | 18.0 GB | 22.7 GB | Too big | Get file → | |
| Q5_K_S | 19.7 GB | 24.4 GB | Too big | Get file → | |
| Q5_K_M | 20.2 GB | 24.9 GB | Too big | Get file → | |
| Q6_K | 23.3 GB | 28.0 GB | Too big | Get file → |
The smallest quant is IQ1_S at 6.73 GB with an estimated 11.4 GB VRAM usage at 8 k context. For 8 GB VRAM, IQ1_S is still above the limit; consider using a higher‑capacity GPU. For 12 GB VRAM, IQ1_S or IQ1_M (7.26 GB, 11.9 GB usage) are suitable. Larger quants such as Q4_K_M (17.34 GB, 22 GB usage) require 24 GB or more.
What GPU do you need for Thai Research Gemma 3 27b It?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is IQ1_M (7.3 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XXS (11.3 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (18.0 GB file, about 22.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (23.3 GB file, about 28.0 GB in use).
Which Thai Research Gemma 3 27b It quant should you choose?
Q4_K_M is the usual starting point for Thai Research Gemma 3 27b It: it balances file size and quality well. Here it is a 17.3 GB file.
If memory is tight, the smallest file is IQ1_S at 6.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Thai Research Gemma 3 27b It
How much VRAM does Thai Research Gemma 3 27b It need?
About 22.0 GB at Q4_K_M with an 8K context window. That is the 17.3 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 Thai Research Gemma 3 27b It on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Thai Research Gemma 3 27b It GGUF?
It depends on the quant: IQ1_S is 6.7 GB, IQ1_M is 7.3 GB, IQ2_XXS is 8.1 GB, IQ2_XS is 8.9 GB, IQ2_S is 9.4 GB, IQ2_M is 10.1 GB and 17 more.
What context length does Thai Research Gemma 3 27b It support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.
Where can I download Thai Research Gemma 3 27b It GGUF?
The files are on Hugging Face in the mradermacher/thai-research-gemma-3-27b-it-i1-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 Thai Research Gemma 3 27b It use?
Hugging Face lists the license as gemma. 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?
The smallest quant requires about 11.4 GB VRAM, so 8 GB is insufficient.
Does it support English text?
The model is primarily trained for Thai; English support is limited.
How do I run it with llama.cpp?
Download the desired GGUF file, install llama‑cpp‑python, and load the file with the provided quant.