moondream2 needs about 3.6 GB of memory at its main file (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.1 GB to 2.8 GB (F16).
Moondream 2 – a compact vision‑language model for edge devices
Moondream 2 is a 1.42 billion‑parameter Llama‑family model with phi2 architecture. It supports vision tasks and runs efficiently on local hardware. The model is released under the Apache‑2.0 license.
Good at
- Vision‑language reasoning
- Object detection
- UI element localization
Limits
- No text‑only tasks beyond vision
- Requires 8 k context for full memory estimates
- No multilingual support beyond English
Best for
- Edge device image captioning
- UI automation scripts
- Document OCR and layout analysis
Who it’s for. Developers building lightweight vision‑language applications on laptops or embedded GPUs. The model is suitable for local inference without cloud dependencies.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.1 GB | 2.0 GB | Fits | Get file → | |
| — | 1.5 GB | 2.4 GB | Fits | Get file → | |
| F16 | 2.8 GB | 3.7 GB | Fits | Get file → |
For 8 GB VRAM, the 1.06 GB unknown quant uses about 3.2 GB at 8 k context, fitting comfortably. If more accuracy is needed and 12 GB VRAM is available, the 2.84 GB F16 quant uses about 5 GB. The 1.51 GB unknown quant is a middle ground with 3.6 GB usage.
What GPU do you need for moondream2?
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 the main file (1.5 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (2.8 GB file, about 5.0 GB in use).
Which moondream2 quant should you choose?
If memory is tight, the smallest file is the first one in the table at 1.1 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 moondream2
How much VRAM does moondream2 need?
About 3.6 GB at its main file with an 8K context window. That is the 1.5 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 moondream2 on an 8 GB GPU?
Yes, with F16: the 2.8 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of moondream2 GGUF?
It depends on the quant: file is 1.1 GB, file is 1.5 GB, F16 is 2.8 GB.
What context length does moondream2 support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.4 GB at 2K.
Where can I download moondream2 GGUF?
The files are on Hugging Face in the cjpais/moondream2-llamafile repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does moondream2 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 Moondream 2 on 8 GB VRAM?
Yes, the 1.06 GB quant uses about 3.2 GB at 8 k context, leaving headroom for other processes.
Does Moondream 2 support text‑only inference?
Moondream 2 is a vision‑language model; it is optimized for image inputs and does not provide dedicated text‑only capabilities.