xyz 002 needs about 2.3 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
xyz 002 is a 1.17B-parameter Xyz model in GGUF format, quantized by moustyb. Its trained context length is 125K tokens. The repository has 1 quant file, from 0.7 GB (Q4_K_M) to 0.7 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.7 GB | 2.3 GB | Fits | Get file → |
What GPU do you need for xyz 002?
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_M (0.7 GB file, about 2.3 GB in use).
Which xyz 002 quant should you choose?
Q4_K_M is the usual starting point for xyz 002: it balances file size and quality well. Here it is a 0.7 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about xyz 002
How much VRAM does xyz 002 need?
About 2.3 GB at Q4_K_M with an 8K context window. That is the 0.7 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 xyz 002 on an 8 GB GPU?
Yes, with Q4_K_M: the 0.7 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of xyz 002 GGUF?
It depends on the quant: Q4_K_M is 0.7 GB.
What context length does xyz 002 support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download xyz 002 GGUF?
The files are on Hugging Face in the moustyb/xyz_002 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does xyz 002 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.