gemma 4 E4B it DASHQ Q2 needs about 5.3 GB of memory at IQ2_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 3.1 GB (IQ2_XXS) to 3.5 GB (Q2_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
Gemma 4 E4B instruction-tuned 2‑bit GGUF model
Gemma 4 E4B it is a 7.5 billion‑parameter instruction‑tuned model. It is quantized to 2‑bit with DASH‑Q and available in three quant variants. The model supports a 131072‑token context window and is licensed under Apache‑2.0.
Good at
- Instruction following
- Reasoning
- Text generation
Limits
- No vision support
- Requires 8‑k context for memory estimates
- No audio or video
Best for
- Local inference on laptops
- Edge device deployment
- Low‑latency chat
Who it’s for. Developers and researchers who need a lightweight, instruction‑tuned Gemma 4 model for on‑device inference. The model is suitable for applications that require a small memory footprint and a large context window.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 3.1 GB | 5.1 GB | Fits | Get file → | |
| IQ2_M | 3.4 GB | 5.3 GB | Fits | Get file → | |
| Q2_K_XL | 3.5 GB | 5.4 GB | Fits | Get file → |
For 8 GB VRAM use IQ2_XXS (file size 3.15 GB, memory 5.1 GB). For 12 GB VRAM use IQ2_M (3.4 GB, 5.3 GB). For 16 GB VRAM use Q2_K_XL (3.53 GB, 5.4 GB). Estimates are approximate.
What GPU do you need for gemma 4 E4B it DASHQ Q2?
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 Q2_K_XL (3.5 GB file, about 5.4 GB in use).
Which gemma 4 E4B it DASHQ Q2 quant should you choose?
IQ2_M (3.4 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ2_XXS at 3.1 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 4 E4B it DASHQ Q2
How much VRAM does gemma 4 E4B it DASHQ Q2 need?
About 5.3 GB at IQ2_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 gemma 4 E4B it DASHQ Q2 on an 8 GB GPU?
Yes, with Q2_K_XL: the 3.5 GB file needs about 5.4 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 DASHQ Q2 GGUF?
It depends on the quant: IQ2_XXS is 3.1 GB, IQ2_M is 3.4 GB, Q2_K_XL is 3.5 GB.
What context length does gemma 4 E4B it DASHQ Q2 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 DASHQ Q2 GGUF?
The files are on Hugging Face in the jkim96/gemma-4-E4B-it-DASHQ-Q2-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 DASHQ Q2 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 IQ2_XXS quant uses about 5.1 GB of VRAM at 8 k context.
Does this model support image input?
No, the GGUF files contain only text; the vision tower is omitted.
What license applies?
The model is released under Apache‑2.0, inherited from the base model.