child gemma4 e2b v5 vision needs about 6.0 GB of memory at Q8_0 (a 4.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 3.8 GB (Q6_K) to 9.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
4.63B multimodal Gemma4 model with vision support
child gemma4 e2b v5 vision is a 4.63B parameter Gemma4 model fine‑tuned for text and image input. It supports a 131072 token context window and is available in three quantized GGUF formats. The model is licensed under gemma and is designed for local deployment.
Good at
- Reasoning with text and image
- Multimodal input handling
- Instruction‑tuned generation
Limits
- No native vision in the text‑only variant
- Requires separate mmproj component for images
- Large memory for higher quant levels
Best for
- Educational image‑to‑text conversion
- Multilingual classroom content generation
- On‑device multimodal chat
Who it’s for. Developers building local AI assistants that need both text and image understanding. Educators wanting to process classroom photos into readable text. Hobbyists deploying models on laptops or mobile devices.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 3.8 GB | 4.9 GB | Fits | Get file → | |
| Q8_0 | 4.9 GB | 6.0 GB | Fits | Get file → | |
| F16 | 9.3 GB | 10.4 GB | Too big | Get file → |
For 8 GB VRAM use Q6_K (3.83 GB file, ~4.9 GB memory at 8K context). For 12 GB VRAM use Q8_0 (4.95 GB file, ~6 GB memory). If more memory is available, F16 (9.27 GB file, ~10.4 GB memory) offers the highest precision.
What GPU do you need for child gemma4 e2b v5 vision?
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 Q8_0 (4.9 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (9.3 GB file, about 10.4 GB in use).
Which child gemma4 e2b v5 vision quant should you choose?
Q8_0 (4.9 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is Q6_K at 3.8 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about child gemma4 e2b v5 vision
How much VRAM does child gemma4 e2b v5 vision need?
About 6.0 GB at Q8_0 with an 8K context window. That is the 4.9 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 child gemma4 e2b v5 vision on an 8 GB GPU?
Yes, with Q8_0: the 4.9 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of child gemma4 e2b v5 vision GGUF?
It depends on the quant: Q6_K is 3.8 GB, Q8_0 is 4.9 GB, F16 is 9.3 GB.
What context length does child gemma4 e2b v5 vision 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 child gemma4 e2b v5 vision GGUF?
The files are on Hugging Face in the mie-edu/child-gemma4-e2b-v5-vision-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 child gemma4 e2b v5 vision 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 this model on 8 GB VRAM?
Yes, the Q6_K quantized file is 3.83 GB and requires about 4.9 GB of VRAM at 8K context.
Do I need a separate vision component?
Yes, the vision capability is provided by an mmproj file that must be downloaded alongside the main model.
What context length does it support?
It supports up to 131072 tokens, allowing very long conversations or documents.