Hf Jinen v2 Small needs about 0.9 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.1 GB (Q4_K_M) to 0.2 GB (F16).
Jinen v2 Small – 109.5M parameter Japanese kanji conversion model
Jinen v2 Small is a 109.5 million parameter model based on the Qwen3 architecture. It is optimized for kanji conversion and requires NFKC normalization of prompts. The model is released under CC BY‑SA 4.0.
Good at
- Kanji conversion
- NFKC‑based text processing
- Small footprint
Limits
- No vision support
- Requires NFKC normalization
- Context limited to 1024 tokens
Best for
- Japanese text correction
- Kanji conversion tasks
- Low‑resource inference
Who it’s for. Developers needing a lightweight Japanese kanji conversion model. Suitable for local inference with limited VRAM. The model is ideal for applications that require strict licensing compliance under CC BY‑SA 4.0.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| F16 | 0.2 GB | 0.8 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M or Q5_K_M (0.07 GB or 0.08 GB) are recommended, each needing about 0.9 GB memory at 8 k context. Q8_0 (0.12 GB) also fits within 8 GB. For higher precision, F16 (0.22 GB) requires about 1 GB memory.
What GPU do you need for Hf Jinen v2 Small?
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 F16 (0.2 GB file, about 1.0 GB in use).
Which Hf Jinen v2 Small quant should you choose?
Q4_K_M is the usual starting point for Hf Jinen v2 Small: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.1 GB, about 1.6 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Hf Jinen v2 Small
How much VRAM does Hf Jinen v2 Small need?
About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.1 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 Hf Jinen v2 Small on an 8 GB GPU?
Yes, with F16: the 0.2 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Hf Jinen v2 Small GGUF?
It depends on the quant: Q4_K_M is 0.1 GB, Q5_K_M is 0.1 GB, Q8_0 is 0.1 GB, F16 is 0.2 GB.
What context length does Hf Jinen v2 Small support?
The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 1K.
Where can I download Hf Jinen v2 Small GGUF?
The files are on Hugging Face in the togatogah/jinen-v2-small.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 Hf Jinen v2 Small use?
Hugging Face lists the license as cc-by-sa-4.0. 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 Jinen v2 Small on 8 GB VRAM?
Yes. Use Q4_K_M or Q5_K_M quantizations; each requires roughly 0.9 GB memory at 8 k context.
Does the model support vision tasks?
No. The model is purely text‑based and has no vision capabilities.
What prompt format does it use?
Prompts must be NFKC normalized and use the same token format as Jinen v1, with greedy decoding (temp 0, top‑k 1).