Gemma-3N-E2B-It needs about 4.0 GB of memory at Q4_K_M (a 3.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 2.1 GB (IQ2_XXS) to 8.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.0 GB.
Gemma‑3N‑E2B‑It: 4.46B‑parameter multimodal model in GGUF format
Gemma‑3N‑E2B‑It is a 4.46B‑parameter model from the Gemma family. It supports multimodal input, including vision, and offers a 32K token context length. The model is available in multiple GGUF quantizations for efficient deployment.
Good at
- Multimodal text and image processing
- Low‑resource inference
- Instruction‑tuned responses
Limits
- No vision support in some quantizations
- Large VRAM needed for higher‑bit quants
- License requires compliance with gemma terms
Best for
- Embedded AI assistants
- Edge device inference
- Fine‑tuning on custom data
Who it’s for. Developers needing a lightweight multimodal LLM for edge or low‑resource environments. The model is suitable for projects that require efficient inference with a 32K context window.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 2.1 GB | 3.1 GB | Fits | Get file → | |
| IQ2_M | 2.2 GB | 3.2 GB | Fits | Get file → | |
| Q2_K | 2.2 GB | 3.2 GB | Fits | Get file → | |
| Q2_K_L | 2.2 GB | 3.2 GB | Fits | Get file → | |
| IQ3_XXS | 2.3 GB | 3.3 GB | Fits | Get file → | |
| Q3_K_S | 2.4 GB | 3.4 GB | Fits | Get file → | |
| Q3_K_M | 2.5 GB | 3.5 GB | Fits | Get file → | |
| Q2_K_XL | 2.6 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_XL | 2.8 GB | 3.9 GB | Fits | Get file → | |
| IQ4_XS | 2.9 GB | 3.9 GB | Fits | Get file → | |
| Q4_0 | 3.0 GB | 4.0 GB | Fits | Get file → | |
| IQ4_NL | 3.0 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_S | 3.0 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_M | 3.0 GB | 4.0 GB | Fits | Get file → | |
| Q4_1 | 3.1 GB | 4.1 GB | Fits | Get file → | |
| Q5_K_S | 3.3 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_M | 3.3 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_XL | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q5_K_XL | 4.0 GB | 5.0 GB | Fits | Get file → | |
| Q6_K | 4.2 GB | 5.2 GB | Fits | Get file → | |
| Q6_K_XL | 4.5 GB | 5.5 GB | Fits | Get file → | |
| Q8_0 | 4.8 GB | 5.8 GB | Fits | Get file → | |
| Q8_K_XL | 7.5 GB | 8.5 GB | Too big | Get file → | |
| F16 | 8.9 GB | 9.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 3.03 GB, estimated memory 4 GB). For 12 GB VRAM, Q5_K_M (file size 3.29 GB, estimated memory 4.3 GB) offers higher precision. For 16 GB VRAM, Q6_K_XL (file size 4.47 GB, estimated memory 5.5 GB) provides a balance of quality and memory usage.
What GPU do you need for Gemma-3N-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: the best quant that fits is Q4_K_M (3.0 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.8 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.8 GB file, about 5.8 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.9 GB file, about 9.9 GB in use).
Which Gemma-3N-E2B-It quant should you choose?
Q4_K_M is the usual starting point for Gemma-3N-E2B-It: it balances file size and quality well. Here it is a 3.0 GB file.
The Q8_0 file is 4.8 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_XXS at 2.1 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
Source
Frequently asked questions about Gemma-3N-E2B-It
How much VRAM does Gemma-3N-E2B-It need?
About 4.0 GB at Q4_K_M with an 8K context window. That is the 3.0 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-3N-E2B-It on an 8 GB GPU?
Yes, with Q8_0: the 4.8 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gemma-3N-E2B-It GGUF?
It depends on the quant: IQ2_XXS is 2.1 GB, IQ2_M is 2.2 GB, Q2_K is 2.2 GB, Q2_K_L is 2.2 GB, IQ3_XXS is 2.3 GB, Q3_K_S is 2.4 GB and 18 more.
What context length does Gemma-3N-E2B-It support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.0 GB at 32K.
Where can I download Gemma-3N-E2B-It GGUF?
The files are on Hugging Face in the Andre2015/gemma-3n-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 Gemma-3N-E2B-It 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 Gemma‑3N‑E2B‑It on 8 GB VRAM?
Yes, use a 4‑bit quant such as Q4_K_M which requires about 4 GB of VRAM at 8K context.
Does the model support image input?
Yes, the model can process vision input, but some quantizations may limit this feature.
What is the maximum context length?
The model supports up to 32,768 tokens as its maximum context length.