Thai Legal Gemma 4B CPT needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 4.4 GB (Q2_K) to 14.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
Thai Legal Gemma 4B CPT – a Gemma model trained on Thai legal data
Thai Legal Gemma 4B CPT is a Gemma-4-E4B model that has undergone Continued Pre-Training on large Thai legal datasets. It has not yet received instruction fine‑tuning or safety alignment and is not ready for production use.
Good at
- Thai legal text generation
- Thai legal terminology understanding
- Legal document drafting assistance
Limits
- Not fine‑tuned for instruction or alignment
- May hallucinate legal content
- Requires ≥18 GB VRAM for full precision
Best for
- Legal research prototyping
- Drafting preliminary Thai legal drafts
- Legal education tools
Who it’s for. Developers building Thai legal applications and researchers exploring Thai legal NLP can use this checkpoint for experimentation and prototyping.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.4 GB | 6.3 GB | Fits | Get file → | |
| Q3_K_S | 4.6 GB | 6.5 GB | Fits | Get file → | |
| Q3_K_M | 4.8 GB | 6.7 GB | Fits | Get file → | |
| Q3_K_L | 5.0 GB | 6.9 GB | Fits | Get file → | |
| IQ4_XS | 5.1 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_S | 5.2 GB | 7.1 GB | Fits | Get file → | |
| Q4_K_M | 5.3 GB | 7.2 GB | Tight | Get file → | |
| Q5_K_S | 5.6 GB | 7.6 GB | Tight | Get file → | |
| Q5_K_M | 5.7 GB | 7.6 GB | Tight | Get file → | |
| Q6_K | 6.2 GB | 8.1 GB | Too big | Get file → | |
| Q8_0 | 8.0 GB | 9.9 GB | Too big | Get file → | |
| F16 | 14.9 GB | 16.9 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (5.3 GB file, 7.2 GB memory) is a good choice. If you have 16 GB VRAM, Q6_K (6.17 GB file, 8.1 GB memory) offers a balance of quality and size. Full precision requires ≥18 GB VRAM.
What GPU do you need for Thai Legal Gemma 4B CPT?
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: the best quant that fits is Q5_K_M (5.7 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (14.9 GB file, about 16.9 GB in use).
Which Thai Legal Gemma 4B CPT quant should you choose?
Q4_K_M is the usual starting point for Thai Legal Gemma 4B CPT: it balances file size and quality well. Here it is a 5.3 GB file.
The Q8_0 file is 8.0 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 Q2_K at 4.4 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 Legal Gemma 4B CPT
How much VRAM does Thai Legal Gemma 4B CPT need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.3 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 Legal Gemma 4B CPT on an 8 GB GPU?
Yes, with Q5_K_M: the 5.7 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Thai Legal Gemma 4B CPT GGUF?
It depends on the quant: Q2_K is 4.4 GB, Q3_K_S is 4.6 GB, Q3_K_M is 4.8 GB, Q3_K_L is 5.0 GB, IQ4_XS is 5.1 GB, Q4_K_S is 5.2 GB and 6 more.
What context length does Thai Legal Gemma 4B CPT support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.
Where can I download Thai Legal Gemma 4B CPT GGUF?
The files are on Hugging Face in the mradermacher/Thai-Legal-Gemma-4B-CPT-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 Legal Gemma 4B CPT 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?
Yes, the Q4_K_M quant uses about 7.2 GB of VRAM at 8k context, which fits within an 8 GB budget with some headroom.
What is the context length?
The model was trained with a context of 131072 tokens, but typical usage is limited to 8k tokens for current quant files.
Is the model safe for production?
No. It has not undergone safety alignment or instruction fine‑tuning and may produce hallucinations, so it is not suitable for production.