Liujgoj Cantonese Gemma4 12b CPT Unified needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 4.8 GB (Q2_K) to 12.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
Liujgoj Cantonese Gemma4 12b CPT Unified – a 11.9B parameter Gemma model
Liujgoj Cantonese Gemma4 12b CPT Unified is a 11.9B parameter Gemma model trained on 262144 context tokens. It supports vision and is released under the apache-2.0 license. The model is available in multiple GGUF quantizations.
Good at
- Vision tasks
- Cantonese language understanding
- Large context handling
Limits
- No vision support in some quantizations
- Large VRAM requirement for higher quants
- License requires attribution
Best for
- Image captioning in Cantonese
- Long-form Cantonese text generation
- Vision‑language integration
Who it’s for. Developers building Cantonese language applications that require vision capabilities. Researchers needing a large‑context model for multimodal tasks. Users who prefer open‑source models with an apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.8 GB | 18.2 GB | Too big | Get file → | |
| Q3_K_S | 5.5 GB | 18.9 GB | Too big | Get file → | |
| Q3_K_M | 6.1 GB | 19.5 GB | Too big | Get file → | |
| Q3_K_L | 6.6 GB | 20.0 GB | Too big | Get file → | |
| IQ4_XS | 6.7 GB | 20.1 GB | Too big | Get file → | |
| Q4_K_S | 7.0 GB | 20.4 GB | Too big | Get file → | |
| Q4_K_M | 7.4 GB | 20.8 GB | Too big | Get file → | |
| Q5_K_S | 8.4 GB | 21.7 GB | Too big | Get file → | |
| Q5_K_M | 8.6 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 23.2 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 26.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (4.85 GB, 18.2 GB memory) or Q3_K_S (5.54 GB, 18.9 GB memory). For 12 GB VRAM, Q4_K_S (7.04 GB, 20.4 GB memory) or Q4_K_M (7.4 GB, 20.8 GB memory) are suitable. Higher quants require more VRAM and RAM.
What GPU do you need for Liujgoj Cantonese Gemma4 12b CPT Unified?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
Which Liujgoj Cantonese Gemma4 12b CPT Unified quant should you choose?
Q4_K_M is the usual starting point for Liujgoj Cantonese Gemma4 12b CPT Unified: it balances file size and quality well. Here it is a 7.4 GB file.
The Q8_0 file is 12.7 GB, about 1.7 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 4.8 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
Frequently asked questions about Liujgoj Cantonese Gemma4 12b CPT Unified
How much VRAM does Liujgoj Cantonese Gemma4 12b CPT Unified need?
About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 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 Liujgoj Cantonese Gemma4 12b CPT Unified on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Liujgoj Cantonese Gemma4 12b CPT Unified GGUF?
It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 5.5 GB, Q3_K_M is 6.1 GB, Q3_K_L is 6.6 GB, IQ4_XS is 6.7 GB, Q4_K_S is 7.0 GB and 5 more.
What context length does Liujgoj Cantonese Gemma4 12b CPT Unified support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.
Where can I download Liujgoj Cantonese Gemma4 12b CPT Unified GGUF?
The files are on Hugging Face in the mradermacher/Liujgoj-Cantonese-Gemma4-12b-CPT-Unified-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 Liujgoj Cantonese Gemma4 12b CPT Unified 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 this model on 8 GB VRAM?
Yes, the Q2_K and Q3_K_S quantizations fit within 8 GB VRAM, with estimated memory usage of 18.2 GB and 18.9 GB respectively.
Does this model support vision?
Yes, the model has detected vision abilities and can process image inputs.
What license does it use?
The model is released under the apache-2.0 license, requiring attribution.