JI

Hf Jinen v2 Xsmall

JinenGGUF by togatogahUpdated 2026-08-20
Download on Hugging Face
Parameters36M
Context1K
Layers6
Architectureqwen3
Smallest quant0.0 GB
Quick answer

Hf Jinen v2 Xsmall needs about 0.6 GB of memory at Q4_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.0 GB (Q4_K_M) to 0.1 GB (F16).

Hf Jinen v2 Xsmall – 35.7M parameter Japanese kanji conversion model

Hf Jinen v2 Xsmall is a 35.7M parameter Qwen3‑based model designed for Japanese kanji conversion. It supports NFKC normalised prompts and requires greedy decoding. The model is released under CC BY‑SA 4.0.

Good at

  • Japanese kanji conversion
  • NFKC normalised text
  • Small footprint

Limits

  • No vision support
  • Requires NFKC normalisation
  • Limited context length 1024 tokens

Best for

  • Local Japanese text conversion
  • Embedded device inference
  • Low‑memory LLM applications

Who it’s for. Developers needing a lightweight Japanese kanji conversion model for local inference. Suitable for applications where GPU memory is limited and strict licensing is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.0 GB 0.5 GB
Fits Get file →
Q5_K_M0.0 GB 0.5 GB
Fits Get file →
Q8_00.0 GB 0.6 GB
Fits Get file →
F160.1 GB 0.6 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M or Q5_K_M (0.03 GB file, ~0.6 GB VRAM at 8k context). For 16 GB VRAM, Q8_0 or F16 are available (0.04 GB and 0.07 GB files). Memory estimates are approximate.

What GPU do you need for Hf Jinen v2 Xsmall?

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 (0.1 GB file, about 0.7 GB in use).

Which Hf Jinen v2 Xsmall quant should you choose?

Q4_K_M is the usual starting point for Hf Jinen v2 Xsmall: it balances file size and quality well. Here it is a 0.0 GB file.

The Q8_0 file is 0.0 GB, about 1.5 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

Architectureqwen3
Parameters36M
Layers6
Trained context1,024 tokens
KV cache (fp16)12 KB per token

Source

Quantized bytogatogah
FamilyJinen
Downloads (HF)931
Last updated2026-08-20

Frequently asked questions about Hf Jinen v2 Xsmall

How much VRAM does Hf Jinen v2 Xsmall need?

About 0.6 GB at Q4_K_M with an 8K context window. That is the 0.0 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 Xsmall on an 8 GB GPU?

Yes, with F16: the 0.1 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Hf Jinen v2 Xsmall GGUF?

It depends on the quant: Q4_K_M is 0.0 GB, Q5_K_M is 0.0 GB, Q8_0 is 0.0 GB, F16 is 0.1 GB.

What context length does Hf Jinen v2 Xsmall support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 1K.

Where can I download Hf Jinen v2 Xsmall GGUF?

The files are on Hugging Face in the togatogah/jinen-v2-xsmall.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 Xsmall 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 this model on 8 GB VRAM?

Yes, the Q4_K_M and Q5_K_M quantisations use about 0.6 GB VRAM at 8k context, fitting comfortably in 8 GB.

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 normalised and use the same token format as jinen‑v1, with greedy decoding (temp 0, top‑k 1).

Similar models

Browse all →

More from togatogah

All by togatogah →

More Jinen models

All Jinen →

Other tiny models

All tiny models →