SARC Taigi LLM 12b needs about 11.0 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 6.5 GB (Q3_K_L) to 12.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
Taigi‑focused 12B Gemini‑3 LLM for dialogue and cultural queries
SARC Taigi LLM 12b is a 11.8B‑parameter Gemini‑3 model fine‑tuned on Taiwanese Taigi data. It supports dialogue, vocabulary lookup, and reasoning in Taigi written in Hàn‑jī or Tâi‑lô. The model is available in GGUF format for inference on consumer hardware.
Good at
- Taigi dialogue and consultation
- Taigi vocabulary retrieval
- Logical reasoning in Taigi
Limits
- No vision support
- Requires 8k context for memory estimates
- License: gemma
Best for
- Chatting in Taigi
- Learning Taigi terms
- Cultural context queries
Who it’s for. Developers building Taiwanese language applications, educators teaching Taigi, and researchers studying regional dialects. The model is suitable for CPU or GPU inference via llama.cpp or Ollama.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 6.5 GB | 10.2 GB | Too big | Get file → | |
| Q4_K_M | 7.3 GB | 11.0 GB | Too big | Get file → | |
| Q6_K | 9.7 GB | 13.4 GB | Too big | Get file → | |
| Q8_0 | 12.5 GB | 16.2 GB | Too big | Get file → |
For 8‑GB VRAM use Q3_K_L (6.48 GB file, ~10.2 GB memory at 8k context). For 12‑GB VRAM use Q4_K_M (7.3 GB file, ~11 GB memory). Larger models like Q6_K or Q8_0 need >13 GB VRAM.
What GPU do you need for SARC Taigi LLM 12b?
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 Q4_K_M (7.3 GB file, about 11.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (9.7 GB file, about 13.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (12.5 GB file, about 16.2 GB in use).
Which SARC Taigi LLM 12b quant should you choose?
Q4_K_M is the usual starting point for SARC Taigi LLM 12b: it balances file size and quality well. Here it is a 7.3 GB file.
The Q8_0 file is 12.5 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 Q3_K_L at 6.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SARC Taigi LLM 12b
How much VRAM does SARC Taigi LLM 12b need?
About 11.0 GB at Q4_K_M with an 8K context window. That is the 7.3 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 SARC Taigi LLM 12b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SARC Taigi LLM 12b GGUF?
It depends on the quant: Q3_K_L is 6.5 GB, Q4_K_M is 7.3 GB, Q6_K is 9.7 GB, Q8_0 is 12.5 GB.
What context length does SARC Taigi LLM 12b support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.
Where can I download SARC Taigi LLM 12b GGUF?
The files are on Hugging Face in the Speech-AI-Research-Center/SARC-Taigi-LLM-12b-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 SARC Taigi LLM 12b 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 Q3_K_L quantization requires about 10.2 GB memory at 8k context, which fits on 8 GB VRAM with some overhead.
Does the model support image inputs?
No, the model has no vision capabilities.
What languages does it understand?
It is specialized for Taigi, using Taiwanese Chinese characters and Romanization.