Gemma4 E2B Dflash2 Android 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 3 quants, from 0.0 GB to 3.1 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
Gemma4 E2B Dflash2 Android – 4.65B multimodal instruction‑tuned model for Android CPU/NPU
Gemma4 E2B Dflash2 Android is a 4.65B parameter model that supports text and image input. It is optimized for local execution on Android devices using the RaInfer engine. The model offers a 131072 token context window and is released under Apache‑2.0.
Good at
- Multimodal text‑image generation
- Instruction‑tuned reasoning
- Local Android deployment
Limits
- Requires RaInfer engine
- No bundled SDK or proprietary runtime
- Experimental image bridge only
Best for
- Mobile AI assistants
- On‑device image captioning
- Local coding helpers
Who it’s for. Developers building Android applications that need on‑device multimodal AI without external SDKs. The model is suitable for edge devices with CPU or NPU support and for developers who prefer open‑source, instruction‑tuned models.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.1 GB | Fits | Get file → | |
| — | 0.0 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_M | 3.1 GB | 4.2 GB | Fits | Get file → |
For devices with 1.5 GB RAM, use the unknown quant file (0.02 GB, ~1.1 GB memory at 8 k context). For 4 GB RAM, the Q4_K_M quant (3.11 GB, ~4.2 GB memory at 8 k context) is recommended. File sizes are approximate.
What GPU do you need for Gemma4 E2B Dflash2 Android?
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 the main file (0.0 GB file, about 1.1 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (3.1 GB file, about 4.2 GB in use).
Which Gemma4 E2B Dflash2 Android quant should you choose?
Q4_K_M is the usual starting point for Gemma4 E2B Dflash2 Android: it balances file size and quality well. Here it is a 3.1 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma4 E2B Dflash2 Android
How much VRAM does Gemma4 E2B Dflash2 Android 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 Gemma4 E2B Dflash2 Android on an 8 GB GPU?
Yes, with Q4_K_M: the 3.1 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gemma4 E2B Dflash2 Android GGUF?
It depends on the quant: file is 0.0 GB, file is 0.0 GB, Q4_K_M is 3.1 GB.
What context length does Gemma4 E2B Dflash2 Android 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 Gemma4 E2B Dflash2 Android GGUF?
The files are on Hugging Face in the RoundRobin237/Gemma4-E2B-Dflash2-Android repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Gemma4 E2B Dflash2 Android 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 an 8 GB VRAM laptop?
The Q4_K_M quant requires about 4.2 GB memory at 8 k context, so it fits on an 8 GB VRAM laptop. The unknown quant needs only ~1.1 GB.
Does this model support audio input?
No, audio support is not included in this E2B variant.
Is a proprietary SDK needed to run it?
No, the model is designed for the open RaInfer engine and does not include any proprietary SDK.