moondream2 needs about 3.0 GB of memory at Q4_K (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU.
Moondream2 – 1.42B phi2 model with vision capability
Moondream2 is a 1.42 billion parameter phi2 model that supports vision tasks. It is available as a GGUF file quantized to Q4_K. The model was released by salivosa and is hosted on the HF repo salivosa/moondream2-gguf.
Good at
- Vision tasks
- Text generation
- Image‑to‑text conversion
Limits
- No vision support beyond image input
- No explicit license information
- Context limited to 2048 tokens
Best for
- Generating captions for images
- Answering questions about pictures
- Creating image descriptions
Who it’s for. Developers and researchers who need a lightweight vision‑enabled LLM for local inference. The model is suitable for edge deployments where memory is limited.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.9 GB | 1.8 GB | Fits | Get file → |
The Q4_K quantization results in a 0.92 GB file. It requires approximately 3 GB of VRAM at 8 k context. For 8 GB VRAM, this quant is suitable. No other quants are available in the file list.
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 Q4_K (0.9 GB file, about 3.0 GB in use).
Which moondream2 quant should you choose?
Q4_K (0.9 GB) is the middle option in this repository. 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 moondream2
How much VRAM does moondream2 need?
About 3.0 GB at Q4_K with an 8K context window. That is the 0.9 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 moondream2 on an 8 GB GPU?
Yes, with Q4_K: the 0.9 GB file needs about 3.0 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: Q4_K is 0.9 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 salivosa/moondream2-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Moondream2 on 8 GB VRAM?
Yes, the Q4_K quant requires about 3 GB of VRAM at 8 k context, leaving headroom on an 8 GB GPU.
Does Moondream2 support text generation?
Yes, it can generate text and also process image inputs for captioning.
What is the context length of Moondream2?
The model supports up to 2048 tokens of context.