aqua-qwen needs about 70.4 GB of memory at Q4_K_M (a 67.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 67.2 GB (Q4_K_M) to 222.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
aqua-qwen is a 111B-parameter Qwen model in GGUF format, quantized by saucam. Its trained context length is 32K tokens. The repository has 2 quant files, from 67.2 GB (Q4_K_M) to 222.4 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 67.2 GB (2 parts) | 70.4 GB | Too big | Get file → | |
| F16 | 222.4 GB (10 parts) | 225.6 GB | Too big | Get file → |
What GPU do you need for aqua-qwen?
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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which aqua-qwen quant should you choose?
Q4_K_M is the usual starting point for aqua-qwen: it balances file size and quality well. Here it is a 67.2 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about aqua-qwen
How much VRAM does aqua-qwen need?
About 70.4 GB at Q4_K_M with an 8K context window. That is the 67.2 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 aqua-qwen on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 70.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of aqua-qwen GGUF?
It depends on the quant: Q4_K_M is 67.2 GB, F16 is 222.4 GB.
What context length does aqua-qwen support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download aqua-qwen GGUF?
The files are on Hugging Face in the saucam/aqua-qwen-0.1-110B-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 aqua-qwen 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.