ddh0_orcamaidxl-17b-32k needs about 20.1 GB of memory at Q4_K_M (a 10.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 7.3 GB (Q2_K) to 18.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 36.2 GB.
17B parameter Llama model with 32k context, available in multiple GGUF quantisations
ddh0_orcamaidxl-17b-32k is a 17.46 B parameter Llama‑based model with a native context length of 32 768 tokens. It is a frankenmerge of Orca‑2‑13b and Noromaid‑v0.2‑13b. The model is distributed in GGUF format and can be run with llama.cpp and compatible GUIs.
Good at
- Large context reasoning
- Alpaca‑style prompting
- Fine‑tuned conversational tasks
Limits
- Requires 8 k context for memory estimates
- No vision support
- License terms from Microsoft Research apply
Best for
- Long‑form dialogue generation
- Context‑heavy Q&A
- Story writing with extended memory
Who it’s for. Users needing a high‑parameter Llama model with extended context for local deployment. Suitable for developers and researchers who can comply with the Microsoft Research License and have sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 7.3 GB | 16.8 GB | Too big | Get file → | |
| Q3_K_S | 7.6 GB | 17.1 GB | Too big | Get file → | |
| Q3_K_M | 8.5 GB | 18.0 GB | Too big | Get file → | |
| Q3_K_L | 9.3 GB | 18.8 GB | Too big | Get file → | |
| Q4_0 | 9.9 GB | 19.4 GB | Too big | Get file → | |
| Q4_K_S | 9.9 GB | 19.5 GB | Too big | Get file → | |
| Q4_K_M | 10.5 GB | 20.1 GB | Too big | Get file → | |
| Q5_0 | 12.0 GB | 21.6 GB | Too big | Get file → | |
| Q5_K_S | 12.0 GB | 21.6 GB | Too big | Get file → | |
| Q5_K_M | 12.4 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 14.3 GB | 23.9 GB | Too big | Get file → | |
| Q8_0 | 18.6 GB | 28.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (10.52 GB file, ~20.1 GB VRAM at 8 k context). For 12 GB VRAM, Q5_K_M (12.36 GB file, ~21.9 GB VRAM). For 16 GB VRAM, Q6_K (14.32 GB file, ~23.9 GB VRAM).
What GPU do you need for ddh0_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 Q6_K (14.3 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (18.6 GB file, about 28.1 GB in use).
Which ddh0_orcamaidxl-17b-32k quant should you choose?
Q4_K_M is the usual starting point for ddh0_orcamaidxl-17b-32k: it balances file size and quality well. Here it is a 10.5 GB file.
The Q8_0 file is 18.6 GB, about 1.8 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 7.3 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 ddh0_orcamaidxl-17b-32k
How much VRAM does ddh0_orcamaidxl-17b-32k need?
About 20.1 GB at Q4_K_M with an 8K context window. That is the 10.5 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 ddh0_orcamaidxl-17b-32k on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ddh0_orcamaidxl-17b-32k GGUF?
It depends on the quant: Q2_K is 7.3 GB, Q3_K_S is 7.6 GB, Q3_K_M is 8.5 GB, Q3_K_L is 9.3 GB, Q4_0 is 9.9 GB, Q4_K_S is 9.9 GB and 6 more.
What context length does ddh0_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 ddh0_orcamaidxl-17b-32k GGUF?
The files are on Hugging Face in the TheBloke/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 ddh0_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.
Can I run this model on 8 GB VRAM?
Use the Q4_K_M quantisation; it requires about 20 GB VRAM at 8 k context, so 8 GB is insufficient.
Does this model support image input?
No, the model has no vision capabilities.
What license applies to this model?
It is subject to the Microsoft Research License due to the Orca‑2‑13b component.