Google Gemma 4 E2B It needs about 4.5 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.4 GB (Q4_K_M) to 3.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
Gemma 4 E2B-it: Tiny multimodal model for text, image, and audio on edge devices
Gemma 4 E2B-it is a 4.6‑billion parameter model optimized for on‑device use. It supports text, image, and audio modalities with a 131072‑token context window. The GGUF quantizations allow deployment on Macs with 8 GB+ VRAM.
Good at
- Multimodal text, image, and audio input
- Large 131072‑token context
- Edge‑friendly deployment
Limits
- Requires separate mmproj.gguf for vision and audio
- No native vision support in the main model file
- License is other, not Apache 2.0
Best for
- On‑device chat assistants
- Multimodal content creation
- Edge AI on Macs
Who it’s for. Developers building lightweight, privacy‑focused AI applications on macOS or other edge platforms. The model is suitable for users who need voice, image, and text understanding without cloud dependency.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 3.4 GB | 4.5 GB | Fits | Get file → | |
| Q6_K | 3.8 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (3.43 GB, ~4.5 GB memory at 8k context). If more VRAM is available, Q6_K (3.85 GB, ~4.9 GB memory) offers slightly higher precision. Both estimates are approximate.
What GPU do you need for Google Gemma 4 E2B 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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q6_K (3.8 GB file, about 4.9 GB in use).
Which Google Gemma 4 E2B It quant should you choose?
Q4_K_M is the usual starting point for Google Gemma 4 E2B It: it balances file size and quality well. Here it is a 3.4 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Google Gemma 4 E2B It
How much VRAM does Google Gemma 4 E2B It need?
About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.4 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 Google Gemma 4 E2B It on an 8 GB GPU?
Yes, with Q6_K: the 3.8 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Google Gemma 4 E2B It GGUF?
It depends on the quant: Q4_K_M is 3.4 GB, Q6_K is 3.8 GB.
What context length does Google Gemma 4 E2B 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 0.6 GB at 8K and 2.3 GB at 32K.
Where can I download Google Gemma 4 E2B It GGUF?
The files are on Hugging Face in the batiai/gemma-4-E2B-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 Google Gemma 4 E2B It use?
Hugging Face lists the license as other. 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 E2B-it on a Mac with 8 GB VRAM?
Yes, the Q4_K_M quantization fits within 8 GB VRAM and uses about 4.5 GB of memory at 8k context.
Do I need a separate mmproj file for vision and audio?
Yes, the main model.gguf handles text only; vision and audio are provided in a separate mmproj.gguf projector.
Is the model licensed under Apache 2.0?
No, the license is listed as other; check the original Hugging Face card for details.