Hy MT2 1.8B JP Manga Finetune v5 needs about 2.2 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
Hy MT2 1.8B JP Manga Finetune v5 – Japanese to English manga translation
Hy MT2 1.8B JP Manga Finetune v5 is a fine‑tuned model for translating Japanese manga dialogue into English. It is based on the 1.8B Hy‑MT2 architecture and optimized for short, self‑contained lines.
Good at
- Japanese → English manga translation
- Short line completion
- Low memory footprint
Limits
- No vision support
- Limited to manga domain
- Requires 8k context for best performance
Best for
- Manga translation apps
- On‑device subtitle generation
- Lightweight translation tasks
Who it’s for. Developers building manga reading apps or subtitle tools that need fast, low‑memory Japanese to English translation. The model is ideal for on‑device inference on smartphones or edge devices.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.1 GB | 2.2 GB | Fits | Get file → |
The Q4_K_M quantization file is 1.13 GB and requires about 2.2 GB of VRAM at 8k context. This is suitable for devices with 4 GB or more VRAM. For tighter budgets, consider a 1.25‑bit AngelSlim quantization if available, which reduces the file to 440 MB.
What GPU do you need for Hy MT2 1.8B JP Manga Finetune v5?
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: the best quant that fits is Q4_K_M (1.1 GB file, about 2.2 GB in use).
Which Hy MT2 1.8B JP Manga Finetune v5 quant should you choose?
Q4_K_M is the usual starting point for Hy MT2 1.8B JP Manga Finetune v5: it balances file size and quality well. Here it is a 1.1 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Hy MT2 1.8B JP Manga Finetune v5
How much VRAM does Hy MT2 1.8B JP Manga Finetune v5 need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Hy MT2 1.8B JP Manga Finetune v5 on an 8 GB GPU?
Yes, with Q4_K_M: the 1.1 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Hy MT2 1.8B JP Manga Finetune v5 GGUF?
It depends on the quant: Q4_K_M is 1.1 GB.
What context length does Hy MT2 1.8B JP Manga Finetune v5 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download Hy MT2 1.8B JP Manga Finetune v5 GGUF?
The files are on Hugging Face in the fumetodev/Hy-MT2-1.8B-JP-Manga-Finetune-v5-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 Hy MT2 1.8B JP Manga Finetune v5 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 Q4_K_M quantized model uses approximately 2.2 GB of VRAM at 8k context, well within an 8 GB budget.
Does it support other language pairs?
This release is specifically fine‑tuned for Japanese → English manga translation; other pairs are not supported.
Is the model free to use?
Yes, it is released under the Apache‑2.0 license, allowing free use and modification.