Miril Drone 2B 1 needs about 4.5 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 9.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
Miril Drone 2B 1 – an open‑weight aerial vision‑language model
Miril Drone 2B 1 is a 4.63B‑parameter VLM built on Gemma4. It processes drone‑view images and text prompts to return structured JSON outputs. The model is trained on a subset of the WALDO dataset and is not a production safety system.
Good at
- Drone‑view scene description
- Aerial visual question answering
- Structured JSON output for operator tools
Limits
- No hidden object counts or bounding boxes
- Not suitable for production safety
- Limited perception of small distant objects
Best for
- Drone delivery zone screening
- First‑response inspection triage
- Infrastructure monitoring
Who it’s for. Developers and researchers building drone‑based perception systems who need an open‑weight VLM that can generate machine‑readable JSON from images and prompts. The model is suitable for prototyping and research, not for safety‑critical deployments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.1 GB | Fits | Get file → | |
| IQ2_M | 2.6 GB | 3.7 GB | Fits | Get file → | |
| IQ3_XXS | 2.7 GB | 3.8 GB | Fits | Get file → | |
| Q2_K | 3.0 GB | 4.1 GB | Fits | Get file → | |
| IQ3_XS | 3.1 GB | 4.2 GB | Fits | Get file → | |
| Q3_K_S | 3.1 GB | 4.2 GB | Fits | Get file → | |
| IQ3_M | 3.2 GB | 4.2 GB | Fits | Get file → | |
| Q3_K_M | 3.2 GB | 4.3 GB | Fits | Get file → | |
| Q3_K_L | 3.3 GB | 4.4 GB | Fits | Get file → | |
| IQ4_XS | 3.3 GB | 4.4 GB | Fits | Get file → | |
| IQ4_NL | 3.4 GB | 4.5 GB | Fits | Get file → | |
| Q4_0 | 3.4 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_S | 3.4 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_M | 3.4 GB | 4.5 GB | Fits | Get file → | |
| Q4_1 | 3.5 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_S | 3.6 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_M | 3.6 GB | 4.7 GB | Fits | Get file → | |
| Q2_K_L | 3.7 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 3.9 GB | 5.0 GB | Fits | Get file → | |
| Q3_K_XL | 3.9 GB | 5.0 GB | Fits | Get file → | |
| Q4_K_L | 4.1 GB | 5.2 GB | Fits | Get file → | |
| Q5_K_L | 4.3 GB | 5.4 GB | Fits | Get file → | |
| Q6_K_L | 4.5 GB | 5.6 GB | Fits | Get file → | |
| Q8_0 | 4.9 GB | 6.0 GB | Fits | Get file → | |
| BF16 | 9.3 GB | 10.4 GB | Too big | Get file → |
For 8 GB VRAM use Q4_0 or Q4_K_S (file size 3.37 GB, memory 4.5 GB). For 12 GB VRAM use Q5_K_M (file size 3.64 GB, memory 4.7 GB). For 16 GB VRAM use Q6_K_L (file size 4.55 GB, memory 5.6 GB).
What GPU do you need for Miril Drone 2B 1?
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 IQ3_XXS (2.7 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (9.3 GB file, about 10.4 GB in use).
Which Miril Drone 2B 1 quant should you choose?
Q4_K_M is the usual starting point for Miril Drone 2B 1: it balances file size and quality well. Here it is a 3.4 GB file.
The Q8_0 file is 4.9 GB, about 1.4 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 Miril Drone 2B 1
How much VRAM does Miril Drone 2B 1 need?
About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.4 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 Miril Drone 2B 1 on an 8 GB GPU?
Yes, with Q8_0: the 4.9 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Miril Drone 2B 1 GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 2.6 GB, IQ3_XXS is 2.7 GB, Q2_K is 3.0 GB, IQ3_XS is 3.1 GB, Q3_K_S is 3.1 GB and 19 more.
What context length does Miril Drone 2B 1 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.
Where can I download Miril Drone 2B 1 GGUF?
The files are on Hugging Face in the bartowski/MirilAI_Miril-Drone-2B-1-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 Miril Drone 2B 1 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 Miril Drone 2B 1 on 8 GB VRAM?
Yes, use the Q4_0 or Q4_K_S quantization, which requires about 4.5 GB of VRAM at 8 k context.
Does the model support vision?
Yes, it accepts an image and a visible text prompt and outputs JSON.
Is this model safe for production use?
No, it is a research demo and not a safety system.