GELab-Zero-4B-preview needs about 4.3 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 26 quants, from 0.0 GB to 8.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
4B vision‑language model for local GUI agent tasks
GELab‑Zero‑4B‑preview is a 4‑billion‑parameter Qwen3‑VL‑based model optimized for local inference. It supports vision, text, and multimodal reasoning with a 262,144‑token context window. The model is released under Apache‑2.0 and is suitable for consumer‑grade hardware.
Good at
- Vision‑guided GUI interaction
- Long‑horizon multimodal reasoning
- Zero‑shot task execution
Limits
- Large context length requires significant VRAM
- No native vision support beyond image input
- Requires llama.cpp for inference
Best for
- Building local GUI agents
- Multimodal research on vision‑language models
- Testing vision‑enabled LLMs on edge devices
Who it’s for. Developers and researchers who need a lightweight, open‑source vision‑language model for local GUI automation. The model is ideal for building privacy‑preserving agents that run on consumer hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| IQ2_XXS | 1.3 GB | 3.0 GB | Fits | Get file → | |
| IQ2_XS | 1.4 GB | 3.2 GB | Fits | Get file → | |
| IQ2_S | 1.5 GB | 3.2 GB | Fits | Get file → | |
| Q2_K_S | 1.5 GB | 3.3 GB | Fits | Get file → | |
| IQ2_M | 1.6 GB | 3.3 GB | Fits | Get file → | |
| Q2_K_M | 1.6 GB | 3.3 GB | Fits | Get file → | |
| IQ3_XXS | 1.8 GB | 3.5 GB | Fits | Get file → | |
| IQ3_XS | 1.8 GB | 3.5 GB | Fits | Get file → | |
| IQ3_M | 2.0 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_S | 2.0 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_M | 2.1 GB | 3.8 GB | Fits | Get file → | |
| IQ4_XS | 2.3 GB | 4.0 GB | Fits | Get file → | |
| IQ4_NL | 2.3 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_S | 2.4 GB | 4.1 GB | Fits | Get file → | |
| Q4_0 | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_1 | 2.5 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_M | 2.6 GB | 4.3 GB | Fits | Get file → | |
| Q5_0 | 2.9 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_M | 3.0 GB | 4.7 GB | Fits | Get file → | |
| Q5_1 | 3.1 GB | 4.9 GB | Fits | Get file → | |
| Q6_K_M | 3.4 GB | 5.1 GB | Fits | Get file → | |
| Q8_0 | 4.3 GB | 6.0 GB | Fits | Get file → | |
| BF16 | 5.9 GB | 7.6 GB | Tight | Get file → | |
| F16 | 5.9 GB | 7.6 GB | Tight | Get file → | |
| BF16 | 8.1 GB | 9.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ4_XS (2.27 GB) or Q4_K_S (2.41 GB). For 12 GB VRAM, Q4_0 (2.46 GB) or Q5_0 (2.92 GB) provide a good balance of size and performance. Higher precision quants such as Q6_K_M (3.4 GB) or Q8_0 (4.28 GB) are suitable for systems with 16 GB or more.
What GPU do you need for GELab-Zero-4B-preview?
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 IQ4_NL (2.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (5.9 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.8 GB in use).
Which GELab-Zero-4B-preview quant should you choose?
Q4_K_M is the usual starting point for GELab-Zero-4B-preview: it balances file size and quality well. Here it is a 2.6 GB file.
The Q8_0 file is 4.3 GB, about 1.7 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 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 GELab-Zero-4B-preview
How much VRAM does GELab-Zero-4B-preview need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.6 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 GELab-Zero-4B-preview on an 8 GB GPU?
Yes, with BF16: the 5.9 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GELab-Zero-4B-preview GGUF?
It depends on the quant: file is 0.0 GB, IQ2_XXS is 1.3 GB, IQ2_XS is 1.4 GB, IQ2_S is 1.5 GB, Q2_K_S is 1.5 GB, IQ2_M is 1.6 GB and 20 more.
What context length does GELab-Zero-4B-preview support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download GELab-Zero-4B-preview GGUF?
The files are on Hugging Face in the Mungert/GELab-Zero-4B-preview-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 GELab-Zero-4B-preview 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 GELab‑Zero‑4B‑preview on 8 GB VRAM?
Yes, using IQ4_XS or Q4_K_S quants keeps VRAM usage below 8 GB, with approximate memory usage of 4 GB at 8k context.
Does the model support video input?
The base model supports video, but the GGUF quantized files are optimized for image input only.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.