OrcaMaidXL 17B 32k needs about 20.3 GB of memory at Q4_K_M (a 10.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 6.7 GB (Q2_K) to 18.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 36.2 GB.
OrcaMaidXL 17B 32k is a 17.5B-parameter Orcamaidxl model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 14 quant files, from 6.7 GB (Q2_K) to 18.7 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 6.7 GB | 16.2 GB | Too big | Get file → | |
| IQ3_XS | 7.4 GB | 16.9 GB | Too big | Get file → | |
| IQ3_S | 7.8 GB | 17.3 GB | Too big | Get file → | |
| Q3_K_S | 7.8 GB | 17.3 GB | Too big | Get file → | |
| IQ3_M | 8.2 GB | 17.8 GB | Too big | Get file → | |
| Q3_K_M | 8.7 GB | 18.2 GB | Too big | Get file → | |
| Q3_K_L | 9.5 GB | 19.0 GB | Too big | Get file → | |
| IQ4_XS | 9.6 GB | 19.1 GB | Too big | Get file → | |
| Q4_K_S | 10.1 GB | 19.7 GB | Too big | Get file → | |
| Q4_K_M | 10.7 GB | 20.3 GB | Too big | Get file → | |
| Q5_K_S | 12.2 GB | 21.8 GB | Too big | Get file → | |
| Q5_K_M | 12.6 GB | 22.1 GB | Too big | Get file → | |
| Q6_K | 14.5 GB | 24.1 GB | Too big | Get file → | |
| Q8_0 | 18.7 GB | 28.3 GB | Too big | Get file → |
What GPU do you need for OrcaMaidXL 17B 32k?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q5_K_M (12.6 GB file, about 22.1 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (18.7 GB file, about 28.3 GB in use).
Which OrcaMaidXL 17B 32k quant should you choose?
Q4_K_M is the usual starting point for OrcaMaidXL 17B 32k: it balances file size and quality well. Here it is a 10.7 GB file.
The Q8_0 file is 18.7 GB, about 1.7 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 Q2_K at 6.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about OrcaMaidXL 17B 32k
How much VRAM does OrcaMaidXL 17B 32k need?
About 20.3 GB at Q4_K_M with an 8K context window. That is the 10.7 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 OrcaMaidXL 17B 32k on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of OrcaMaidXL 17B 32k GGUF?
It depends on the quant: Q2_K is 6.7 GB, IQ3_XS is 7.4 GB, IQ3_S is 7.8 GB, Q3_K_S is 7.8 GB, IQ3_M is 8.2 GB, Q3_K_M is 8.7 GB and 8 more.
What context length does OrcaMaidXL 17B 32k support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 9.1 GB at 8K and 36.2 GB at 32K.
Where can I download OrcaMaidXL 17B 32k GGUF?
The files are on Hugging Face in the mradermacher/OrcaMaidXL-17B-32k-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 OrcaMaidXL 17B 32k use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.