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 – 1.4B phi2 model with vision capability
Moondream2 is a 1.4‑billion parameter phi2 model trained on 2048‑token context. It supports vision tasks and is available in a single F16 quantized GGUF file. The model has no additional license restrictions listed.
Good at
- Vision‑enabled text generation
- Image captioning
- Multimodal reasoning
Limits
- No explicit license info
- Only F16 quant available
- Requires 5 GB VRAM at 8K context
Best for
- Generating image captions
- Answering image‑based questions
- Embedding image context into text
Who it’s for. Developers needing a lightweight vision‑capable LLM for local inference. Suitable for projects that can run the 2.84 GB F16 GGUF file on a GPU with at least 5 GB VRAM at 8K context.
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 requires roughly 5 GB VRAM when running with an 8K context. For lower memory budgets, no alternative quants are provided.
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 moondream/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 F16 quant needs about 5 GB VRAM at 8K context, leaving headroom for other processes.
Does Moondream2 support text‑only inference?
Yes, it can process text prompts, but its primary design is for vision‑enabled tasks.