Liujgoj Cantonese Gemma 4 12B It Sft 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 25 quants, from 0.0 GB to 9.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
Liujgoj Cantonese Gemma 4 12B It Sft – a Cantonese Romanization dialogue model
Liujgoj Cantonese Gemma 4 12B It Sft is a 11.9‑billion‑parameter Gemma 4 model fine‑tuned for Cantonese Romanization. It supports reasoning and tool use and was trained with a 262144‑token context window.
Good at
- Cantonese Romanization
- Multitask dialogue
- Reasoning and tool use
Limits
- No vision support
- Large VRAM requirement
- Apache‑2.0 license
Best for
- Cantonese chatbots
- Translation tasks
- Tool‑assisted workflows
Who it’s for. Developers building Cantonese‑focused assistants or translation tools. The model is ready to use after downloading the GGUF file and loading it with llama.cpp or transformers.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 13.4 GB | Too big | Get file → | |
| IQ1_S | 3.0 GB | 16.4 GB | Too big | Get file → | |
| IQ1_M | 3.2 GB | 16.6 GB | Too big | Get file → | |
| IQ2_XXS | 3.6 GB | 17.0 GB | Too big | Get file → | |
| IQ2_XS | 3.9 GB | 17.3 GB | Too big | Get file → | |
| IQ2_S | 4.1 GB | 17.5 GB | Too big | Get file → | |
| IQ2_M | 4.4 GB | 17.8 GB | Too big | Get file → | |
| Q2_K_S | 4.5 GB | 17.9 GB | Too big | Get file → | |
| Q2_K | 4.8 GB | 18.2 GB | Too big | Get file → | |
| IQ3_XXS | 4.9 GB | 18.2 GB | Too big | Get file → | |
| IQ3_XS | 5.3 GB | 18.7 GB | Too big | Get file → | |
| IQ3_S | 5.5 GB | 18.9 GB | Too big | Get file → | |
| Q3_K_S | 5.5 GB | 18.9 GB | Too big | Get file → | |
| IQ3_M | 5.8 GB | 19.1 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 | 20.0 GB | Too big | Get file → | |
| IQ4_NL | 7.0 GB | 20.4 GB | Too big | Get file → | |
| Q4_0 | 7.0 GB | 20.4 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 → | |
| Q4_1 | 7.7 GB | 21.1 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 → |
For 8 GB VRAM, use IQ1_S (3 GB, 16.4 GB memory) or IQ1_M (3.22 GB, 16.6 GB memory). If 12 GB VRAM is available, IQ2_XS (3.9 GB, 17.3 GB memory) or Q2_K (4.85 GB, 18.2 GB memory) are suitable. Higher‑quality quants such as Q4_K_M (7.4 GB, 20.8 GB memory) require more VRAM but provide better fidelity.
What GPU do you need for Liujgoj Cantonese Gemma 4 12B It Sft?
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: the best quant that fits is the main file (0.0 GB file, about 13.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 23.2 GB in use).
Which Liujgoj Cantonese Gemma 4 12B It Sft quant should you choose?
Q4_K_M is the usual starting point for Liujgoj Cantonese Gemma 4 12B It Sft: it balances file size and quality well. Here it is a 7.4 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 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
Frequently asked questions about Liujgoj Cantonese Gemma 4 12B It Sft
How much VRAM does Liujgoj Cantonese Gemma 4 12B It Sft 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 Gemma 4 12B It Sft on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Liujgoj Cantonese Gemma 4 12B It Sft GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 3.0 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.6 GB, IQ2_XS is 3.9 GB, IQ2_S is 4.1 GB and 19 more.
What context length does Liujgoj Cantonese Gemma 4 12B It Sft 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 Gemma 4 12B It Sft GGUF?
The files are on Hugging Face in the mradermacher/Liujgoj-Cantonese-gemma-4-12B-it-sft-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 Liujgoj Cantonese Gemma 4 12B It Sft 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, use the IQ1_S or IQ1_M quant, which are 3 GB and 3.22 GB respectively and require about 16.4–16.6 GB of VRAM at 8k context.
Does this model support image input?
No, the model is a text‑only model and does not include vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.