moondream2 needs about 5.0 GB of memory at F16 (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU.
Moondream2 – 1.42B phi2 model with vision support
Moondream2 is a 1.42B parameter phi2 architecture model. It supports vision tasks and is released under the apache-2.0 license. The GGUF file is 2.84 GB and requires about 5 GB of VRAM at 8 k context.
Good at
- Vision‑enabled text generation
- Image captioning
- Multimodal dialogue
Limits
- No vision support in llama.cpp without custom code
- Requires 8 k context for full performance
- Single quant available
Best for
- Image captioning in lightweight setups
- Multimodal chatbots
- Rapid prototyping of vision models
Who it’s for. Developers needing a small vision‑enabled LLM for local deployment. Suitable for projects that can run 8 k context and have at least 5 GB of VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 2.8 GB | 3.7 GB | Fits | Get file → |
The only available quant is F16, 2.84 GB in size. It needs roughly 5 GB of VRAM at 8 k context. For lower VRAM budgets, no other quant is provided, so the model cannot be run efficiently on less than 5 GB of VRAM.
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: no quant fits at an 8K context.
- 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?
F16 (2.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
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 5.0 GB at F16 with an 8K context window. That is the 2.8 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 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: 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 Hahasb/moondream2-20250414-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 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 Moondream2 on 8 GB VRAM?
Yes, the F16 quant requires about 5 GB of VRAM at 8 k context, leaving headroom for 8 GB VRAM.
Does the model support vision in llama.cpp?
The GGUF includes vision support, but llama.cpp may need custom handling for the tokenizer.chat_template field.