GE

Gemma-4-E4B-It

GemmaGGUF by ente-aiUpdated 2026-08-05
Download on Hugging Face
Parameters7.5B
Context128K
Layers42
Architecturegemma4
Smallest quant0.1 GB
Quick answer

Gemma-4-E4B-It needs about 6.9 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.1 GB (Q8_0) to 15.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Gemma‑4‑E4B‑It: 7.5B multimodal instruction‑tuned model

Gemma‑4‑E4B‑It is a 7.5B parameter model from the Gemma 4 family. It supports text and image input and outputs text. The model is instruction‑tuned and licensed under Apache‑2.0.

Good at

  • Multimodal text‑image tasks
  • Instruction‑driven generation
  • Reasoning with large context

Limits

  • No native vision support in GGUF
  • Large memory requirement for high‑quality quants
  • Limited to text output

Best for

  • Local inference on laptops
  • Edge devices with 8 GB VRAM
  • Multimodal chat applications

Who it’s for. Developers needing a multimodal LLM that can run locally. The model is suitable for applications that require instruction‑based text generation with image understanding, such as chatbots or content creation tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.1 GB 2.0 GB
Fits Get file →
—0.1 GB 2.0 GB
Fits Get file →
BF160.2 GB 2.1 GB
Fits Get file →
F160.2 GB 2.1 GB
Fits Get file →
IQ2_M3.5 GB 5.5 GB
Fits Get file →
IQ3_XXS3.7 GB 5.6 GB
Fits Get file →
Q2_K_XL3.8 GB 5.7 GB
Fits Get file →
Q3_K_S3.9 GB 5.8 GB
Fits Get file →
Q3_K_M4.1 GB 6.0 GB
Fits Get file →
Q3_K_XL4.6 GB 6.5 GB
Fits Get file →
IQ4_XS4.7 GB 6.6 GB
Fits Get file →
IQ4_NL4.8 GB 6.7 GB
Fits Get file →
Q4_04.8 GB 6.7 GB
Fits Get file →
Q4_K_S4.8 GB 6.8 GB
Fits Get file →
Q4_K_M5.0 GB 6.9 GB
Fits Get file →
Q4_15.1 GB 7.0 GB
Fits Get file →
Q4_K_XL5.1 GB 7.0 GB
Fits Get file →
Q5_K_S5.4 GB 7.3 GB
Tight Get file →
Q5_K_M5.5 GB 7.4 GB
Tight Get file →
Q5_K_XL6.7 GB 8.6 GB
Too big Get file →
Q6_K7.1 GB 9.0 GB
Too big Get file →
Q6_K_XL7.5 GB 9.4 GB
Too big Get file →
Q8_08.2 GB 10.1 GB
Too big Get file →
Q8_K_XL8.7 GB 10.6 GB
Too big Get file →
BF1615.1 GB 17.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (est. 6.9 GB at 8k context). For 12 GB VRAM, Q5_K_M (est. 7.4 GB) or Q6_K (est. 9 GB). For 16 GB VRAM, Q6_K_XL (est. 9.4 GB) or Q8_0 (est. 10.1 GB).

What GPU do you need for Gemma-4-E4B-It?

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 BF16 (0.2 GB file, about 2.1 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.1 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.5 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_K_XL (8.7 GB file, about 10.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_K_XL (8.7 GB file, about 10.6 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (15.1 GB file, about 17.0 GB in use).

Which Gemma-4-E4B-It quant should you choose?

Q4_K_M is the usual starting point for Gemma-4-E4B-It: it balances file size and quality well. Here it is a 5.0 GB file.

The Q8_0 file is 0.1 GB, about 0.0 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 Q8_0 at 0.1 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters7.5B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized byente-ai
FamilyGemma
Licenseapache-2.0
Downloads (HF)3,878
Last updated2026-08-05

Frequently asked questions about Gemma-4-E4B-It

How much VRAM does Gemma-4-E4B-It need?

About 6.9 GB at Q4_K_M with an 8K context window. That is the 5.0 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 Gemma-4-E4B-It on an 8 GB GPU?

Yes, with Q5_K_M: the 5.5 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma-4-E4B-It GGUF?

It depends on the quant: Q8_0 is 0.1 GB, file is 0.1 GB, BF16 is 0.2 GB, F16 is 0.2 GB, IQ2_M is 3.5 GB, IQ3_XXS is 3.7 GB and 19 more.

What context length does Gemma-4-E4B-It 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-It GGUF?

The files are on Hugging Face in the ente-ai/gemma-4-E4B-it-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 Gemma-4-E4B-It 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 Gemma‑4‑E4B‑It on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires approximately 6.9 GB at 8k context.

Does this model support image input?

Yes, Gemma‑4‑E4B‑It handles text and image input but outputs only text.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of gemma-4-E4B-it

Similar models

Browse all →

More from ente-ai

All by ente-ai →

More Gemma models

All Gemma →

Other small models

All small models →