GE

gemma 4 E2B it UD japanese imatrix

GemmaGGUF by dahara1Updated 2026-04-29
Download on Hugging Face
Parameters4.65B
Context128K
Layers35
Architecturegemma4
Smallest quant2.3 GB
Quick answer

gemma 4 E2B it UD japanese imatrix needs about 4.2 GB of memory at Q4_K_M (a 3.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 20 quants, from 2.3 GB (IQ2_M) to 5.3 GB (Q8_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

Gemma 4 E2B it UD Japanese imatrix – a small, multimodal GGUF model

Gemma 4 E2B it UD Japanese imatrix is a 4.65 billion‑parameter model fine‑tuned for Japanese text and image input. It supports a 131072‑token context window and is available in multiple quantizations. The model is released under Apache 2.0.

Good at

  • Japanese text generation
  • Multimodal image input
  • Reasoning with large context

Limits

  • No vision support beyond images
  • Requires 8 GB RAM for Q4 variants
  • No audio support in this variant

Best for

  • Japanese chatbots
  • Image captioning in Japanese
  • Local inference on laptops

Who it’s for. Developers needing a lightweight Japanese‑focused multimodal model for local deployment. The model runs on llama.cpp and can be used without a GPU, though higher RAM is recommended for larger quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M2.3 GB 3.4 GB
Fits Get file →
IQ3_XXS2.4 GB 3.5 GB
Fits Get file →
Q2_K_XL2.4 GB 3.5 GB
Fits Get file →
Q3_K_S2.4 GB 3.5 GB
Fits Get file →
Q3_K_M2.5 GB 3.6 GB
Fits Get file →
Q3_K_XL2.9 GB 4.0 GB
Fits Get file →
IQ4_XS3.0 GB 4.1 GB
Fits Get file →
IQ4_NL3.0 GB 4.1 GB
Fits Get file →
Q4_03.0 GB 4.1 GB
Fits Get file →
Q4_K_S3.0 GB 4.1 GB
Fits Get file →
Q4_K_M3.1 GB 4.2 GB
Fits Get file →
Q4_13.2 GB 4.2 GB
Fits Get file →
Q4_K_XL3.2 GB 4.3 GB
Fits Get file →
Q5_K_S3.3 GB 4.4 GB
Fits Get file →
Q5_K_M3.4 GB 4.4 GB
Fits Get file →
Q5_K_XL3.7 GB 4.8 GB
Fits Get file →
Q6_K3.9 GB 5.0 GB
Fits Get file →
Q6_K_XL4.7 GB 5.8 GB
Fits Get file →
Q8_05.0 GB 6.1 GB
Fits Get file →
Q8_K_XL5.3 GB 6.4 GB
Fits Get file →

For 8 GB RAM, use Q4_K_M (3.11 GB file, ~4.2 GB VRAM). If 12 GB RAM is available, Q5_K_S (3.32 GB file, ~4.4 GB VRAM) offers better quality. Larger quantizations such as Q6_K_XL require 5.8 GB VRAM and are suitable for servers.

What GPU do you need for gemma 4 E2B it UD japanese imatrix?

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 Q3_K_XL (2.9 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K_XL (4.7 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_K_XL (5.3 GB file, about 6.4 GB in use).

Which gemma 4 E2B it UD japanese imatrix quant should you choose?

Q4_K_M is the usual starting point for gemma 4 E2B it UD japanese imatrix: it balances file size and quality well. Here it is a 3.1 GB file.

The Q8_0 file is 5.0 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.

If memory is tight, the smallest file is IQ2_M at 2.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters4.65B
Layers35
Trained context131,072 tokens
KV cache (fp16)70 KB per token

Source

Quantized bydahara1
FamilyGemma
Licenseapache-2.0
Downloads (HF)3,297
Last updated2026-04-29

Frequently asked questions about gemma 4 E2B it UD japanese imatrix

How much VRAM does gemma 4 E2B it UD japanese imatrix need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 3.1 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 gemma 4 E2B it UD japanese imatrix on an 8 GB GPU?

Yes, with Q8_K_XL: the 5.3 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gemma 4 E2B it UD japanese imatrix GGUF?

It depends on the quant: IQ2_M is 2.3 GB, IQ3_XXS is 2.4 GB, Q2_K_XL is 2.4 GB, Q3_K_S is 2.4 GB, Q3_K_M is 2.5 GB, Q3_K_XL is 2.9 GB and 14 more.

What context length does gemma 4 E2B it UD japanese imatrix support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.

Where can I download gemma 4 E2B it UD japanese imatrix GGUF?

The files are on Hugging Face in the dahara1/gemma-4-E2B-it-UD-japanese-imatrix 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 E2B it UD japanese imatrix 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 quantization requires about 4.2 GB VRAM at 8k context, which fits within an 8 GB GPU.

Does this model support audio input?

No, audio support is only available on the E2B and E4B models, not on this specific Japanese‑imatrix variant.

What license does this model use?

The model is released under the Apache 2.0 license.

Other GGUFs of gemma-4-E2B-it

Similar models

Browse all →

More from dahara1

All by dahara1 →

More Gemma models

All Gemma →

Other small models

All small models →