GE

Gemma 4 E4B xReadable zhTW OCR v1

GemmaGGUF by xCloudinfoUpdated 2026-10-26
Download on Hugging Face
Parameters7.46B
Context128K
Layers42
Architecturegemma4
Smallest quant5.3 GB
Quick answer

Gemma 4 E4B xReadable zhTW OCR v1 needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Gemma 4 E4B xReadable zhTW OCR v1 – a 7.5B multimodal OCR model for Traditional Chinese

Gemma 4 E4B xReadable zhTW OCR v1 is a 7.5‑billion‑parameter multimodal model fine‑tuned for Traditional Chinese OCR. It supports text and image input and outputs Traditional Chinese text. The model is available in GGUF format and can be run locally with llama.cpp or Ollama.

Good at

  • Traditional Chinese OCR
  • Multimodal text and image processing
  • Local on‑device inference

Limits

  • Requires mmproj‑f16 visual projector for image input
  • No audio support
  • License is Gemma Terms – no EU multimodal restriction

Best for

  • Digitizing Taiwanese documents
  • OCR preprocessing for invoices and notes
  • Local OCR on laptops and servers

Who it’s for. Developers building Taiwanese OCR solutions who need a local, privacy‑preserving model. The model is suitable for edge devices and servers that can load a 5 GB GGUF file and the 0.9 GB mmproj visual projector.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M5.3 GB 7.2 GB
Tight Get file →

For 8 GB VRAM use the Q4_K_M GGUF (5.3 GB). The model needs the mmproj‑f16 projector (~0.9 GB). Total memory is about 6 GB, which fits most consumer GPUs. If more VRAM is available, the unquantized safetensors can be used for higher accuracy.

What GPU do you need for Gemma 4 E4B xReadable zhTW OCR v1?

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 Q4_K_M (5.3 GB file, about 7.2 GB in use).

Which Gemma 4 E4B xReadable zhTW OCR v1 quant should you choose?

Q4_K_M is the usual starting point for Gemma 4 E4B xReadable zhTW OCR v1: it balances file size and quality well. Here it is a 5.3 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters7.46B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized byxCloudinfo
FamilyGemma
Licensegemma
Downloads (HF)4,707
Last updated2026-10-26

Frequently asked questions about Gemma 4 E4B xReadable zhTW OCR v1

How much VRAM does Gemma 4 E4B xReadable zhTW OCR v1 need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.3 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 Gemma 4 E4B xReadable zhTW OCR v1 on an 8 GB GPU?

Yes, with Q4_K_M: the 5.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma 4 E4B xReadable zhTW OCR v1 GGUF?

It depends on the quant: Q4_K_M is 5.3 GB.

What context length does Gemma 4 E4B xReadable zhTW OCR v1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download Gemma 4 E4B xReadable zhTW OCR v1 GGUF?

The files are on Hugging Face in the xCloudinfo/Gemma-4-E4B-xReadable-zhTW-OCR-v1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Gemma 4 E4B xReadable zhTW OCR v1 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 Q4_K_M GGUF is 5.3 GB and the mmproj projector is 0.9 GB, totaling about 6 GB, which fits 8 GB VRAM.

Does this model support audio input?

No, audio is not supported in this E4B variant.

What language does the model output?

The model outputs Traditional Chinese (繁體中文) only.

Other GGUFs of gemma-4-E4B-it

Similar models

Browse all →

More from xCloudinfo

All by xCloudinfo →

More Gemma models

All Gemma →

Other small models

All small models →