C3TR Adapter needs about 9.1 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 7 quants, from 3.8 GB (IQ3_XXS) to 10.7 GB (F16).
Gemma‑2 based Japanese‑English translation model in GGUF format
C3TR Adapter is a 9.24‑billion‑parameter Gemma‑2 model converted to GGUF for CPU use. It supports 8192‑token context and is optimized for translation tasks. The model is available in seven quantized variants.
Good at
- Japanese‑English translation
- Casual conversation translation
- Low‑memory inference
Limits
- No vision support
- Requires 8k context for full performance
- License is gemma
Best for
- Translation of informal text
- Local inference on PCs without GPU
- Educational demos
Who it’s for. Users needing a lightweight translation model for Japanese and English, especially on machines without GPUs. It is suitable for developers and researchers working with local LLM inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 3.8 GB | 7.1 GB | Fits | Get file → | |
| Q3_K_M | 4.8 GB | 8.1 GB | Too big | Get file → | |
| Q4_K_M | 5.8 GB | 9.1 GB | Too big | Get file → | |
| F16 | 6.8 GB | 10.2 GB | Too big | Get file → | |
| F16 | 7.7 GB | 11.0 GB | Too big | Get file → | |
| F16 | 8.7 GB | 12.0 GB | Too big | Get file → | |
| F16 | 10.7 GB | 14.0 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ3_XXS (file size 3.8 GB, memory 7.1 GB). For 12‑GB VRAM, Q4_K_M (5.76 GB, 9.1 GB) offers a good balance. For higher quality and more memory, choose F16 variants.
What GPU do you need for C3TR Adapter?
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 IQ3_XXS (3.8 GB file, about 7.1 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.7 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is F16 (10.7 GB file, about 14.0 GB in use).
Which C3TR Adapter quant should you choose?
Q4_K_M is the usual starting point for C3TR Adapter: it balances file size and quality well. Here it is a 5.8 GB file.
If memory is tight, the smallest file is IQ3_XXS at 3.8 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 C3TR Adapter
How much VRAM does C3TR Adapter need?
About 9.1 GB at Q4_K_M with an 8K context window. That is the 5.8 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 C3TR Adapter on an 8 GB GPU?
Yes, with IQ3_XXS: the 3.8 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of C3TR Adapter GGUF?
It depends on the quant: IQ3_XXS is 3.8 GB, Q3_K_M is 4.8 GB, Q4_K_M is 5.8 GB, F16 is 6.8 GB, F16 is 7.7 GB, F16 is 8.7 GB and 1 more.
What context length does C3TR Adapter support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.8 GB at 8K and 2.8 GB at 8K.
Where can I download C3TR Adapter GGUF?
The files are on Hugging Face in the webbigdata/C3TR-Adapter_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 C3TR Adapter 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 C3TR Adapter on 8 GB VRAM?
Yes, the IQ3_XXS quantization uses 7.1 GB of memory at 8k context, fitting within 8 GB VRAM.
Does the model support formal text translation?
Formal text translation performance is slightly lower; for formal texts, use Version 1 of the model.
What special tokens are needed in prompts?
Version 3 adds special tokens ( ) to the prompt template; include them for correct operation.