VLX Seek 1.5 10B needs about 1.0 GB of memory at F32 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 0.0 GB (F32) to 17.9 GB (F16).
VLX Seek 1.5 10B – fine‑grained visual grounding for edge devices
VLX Seek 1.5 10B is a 10B‑parameter model optimized for embodied visual perception. It uses region‑reference localization and a stronger auxiliary vision tower. The model is open‑source under Apache‑2.0 and runs with llama.cpp.
Good at
- Open‑vocabulary object detection
- Region‑level visual grounding
- Embodied scene understanding
Limits
- No vision support in the base model
- Requires three GGUF files
- Large VRAM needed for full precision
Best for
- Drone‑view perception
- Robot‑centric spatial reasoning
- Edge‑side visual intelligence modules
Who it’s for. Researchers and developers building fine‑grained multimodal perception systems for drones, robots, and surveillance. The model is suitable for edge deployments where accurate localization and object counting are required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F32 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| F32 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q8_0 | 1.4 GB | 2.1 GB | Fits | Get file → | |
| F16 | 2.2 GB | 2.9 GB | Fits | Get file → | |
| Q8_0 | 9.5 GB | 11.2 GB | Too big | Get file → | |
| F16 | 17.9 GB | 20.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q8_0 (file size 1.45 GB, estimated 2.1 GB memory at 8 k context). For 16 GB VRAM, use Q8_0 (file size 9.53 GB, estimated 11.2 GB memory) or F16 (file size 17.92 GB, estimated 20.6 GB memory). Lower‑precision Q8_0 reduces VRAM usage while keeping performance close to full precision.
What GPU do you need for VLX Seek 1.5 10B?
These figures add the file size, an fp16 KV cache at an 8K context window 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 F16 (2.2 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (2.2 GB file, about 2.9 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (2.2 GB file, about 2.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.2 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (17.9 GB file, about 20.6 GB in use).
Which VLX Seek 1.5 10B quant should you choose?
F32 (0.4 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.
If memory is tight, the smallest file is F32 at 0.0 GB, with the quality trade-offs that come with fewer bits. 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 VLX Seek 1.5 10B
How much VRAM does VLX Seek 1.5 10B need?
About 1.0 GB at F32 with an 8K context window. That is the 0.4 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 VLX Seek 1.5 10B on an 8 GB GPU?
Yes, with F16: the 2.2 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of VLX Seek 1.5 10B GGUF?
It depends on the quant: F32 is 0.0 GB, Q8_0 is 0.1 GB, F16 is 0.2 GB, F32 is 0.4 GB, Q8_0 is 1.4 GB, F16 is 2.2 GB and 2 more.
Where can I download VLX Seek 1.5 10B GGUF?
The files are on Hugging Face in the Asher-1/VLX-Seek-1.5-10B-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 VLX Seek 1.5 10B 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 VLX Seek 1.5 10B on 8 GB VRAM?
Yes, using the Q8_0 quantization (1.45 GB file, ~2.1 GB memory at 8 k context).
Does the model support vision input?
Yes, it includes a vision stack and a detector, but the GGUF files must be combined for full functionality.
What license applies to this model?
The model is released under the Apache‑2.0 license.