Gemma 4 E2B it Artemis needs about 2.3 GB of memory at IQ2_M (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.1 GB (Q4_0) to 2.3 GB (Q3_K_L). Longer context needs more: at 32K tokens the KV cache alone adds about 0.3 GB.
Gemma 4 E2B it Artemis – 4.63B parameter chat model with vision and tool calling
Gemma 4 E2B it Artemis is a 4.63B parameter assistant model from Google DeepMind, quantized with QAT for efficient deployment. It supports text, image, and tool‑calling inputs and is available in multiple GGUF quantizations.
Good at
- Text and image reasoning
- Tool calling
- Multimodal chat
Limits
- No video or audio support
- Requires QAT quantization
- No vision projector without extra download
Best for
- Chatbots on CPUs
- Tool‑enabled assistants
- Vision‑aware text generation
Who it’s for. Developers building lightweight multimodal assistants who need a small footprint and tool‑calling capability. The model is ideal for CPU‑only inference with llama.cpp or vLLM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| — | 0.1 GB | 0.6 GB | Fits | Get file → | |
| IQ2_M | 1.8 GB | 2.3 GB | Fits | Get file → | |
| IQ3_XXS | 2.1 GB | 2.6 GB | Fits | Get file → | |
| Q3_K_M | 2.2 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_L | 2.3 GB | 2.9 GB | Fits | Get file → |
For 8 GB VRAM, the Q4_0 file (0.08 GB, 0.6 GB memory at 8 k context) is ideal. If more memory is available, Q3_K_L (2.31 GB, 2.9 GB memory) offers higher quality. The IQ2_M and IQ3_XXS files require 2.3–2.6 GB memory and are suitable for larger VRAM setups.
What GPU do you need for Gemma 4 E2B it Artemis?
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 Q3_K_L (2.3 GB file, about 2.9 GB in use).
Which Gemma 4 E2B it Artemis quant should you choose?
IQ2_M (1.8 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 Q4_0 at 0.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma 4 E2B it Artemis
How much VRAM does Gemma 4 E2B it Artemis need?
About 2.3 GB at IQ2_M with an 8K context window. That is the 1.8 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 E2B it Artemis on an 8 GB GPU?
Yes, with Q3_K_L: the 2.3 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gemma 4 E2B it Artemis GGUF?
It depends on the quant: Q4_0 is 0.1 GB, file is 0.1 GB, IQ2_M is 1.8 GB, IQ3_XXS is 2.1 GB, Q3_K_M is 2.2 GB, Q3_K_L is 2.3 GB.
What context length does Gemma 4 E2B it Artemis support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.3 GB at 32K.
Where can I download Gemma 4 E2B it Artemis GGUF?
The files are on Hugging Face in the turintech/gemma-4-E2B-it-Artemis-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 E2B it Artemis 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 E2B it Artemis on 8 GB VRAM?
Yes, the Q4_0 quantization uses 0.6 GB memory at 8 k context, well within 8 GB VRAM limits.
Does the model support vision?
Yes, it handles image input; a separate projector download is required for vision.
What license applies?
The model is released under the Apache 2.0 license.