Qwerky 72B needs about 49.8 GB of memory at Q3_K_M (a 44.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 35.7 GB (Q2_K) to 47.8 GB (IQ4_XS).
Qwerky 72B is a 79.3B-parameter Qrwkv model in GGUF format, quantized by mradermacher. Its trained context length is 1024K tokens. The repository has 5 quant files, from 35.7 GB (Q2_K) to 47.8 GB (IQ4_XS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 35.7 GB | 40.5 GB | Too big | Get file → | |
| Q3_K_S | 41.5 GB | 47.0 GB | Too big | Get file → | |
| Q3_K_M | 44.0 GB | 49.8 GB | Too big | Get file → | |
| Q3_K_L | 45.1 GB | 51.1 GB | Too big | Get file → | |
| IQ4_XS | 47.8 GB | 54.0 GB | Too big | Get file → |
What GPU do you need for Qwerky 72B?
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: 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: the best quant that fits is Q3_K_S (41.5 GB file, about 47.0 GB in use).
Which Qwerky 72B quant should you choose?
Q3_K_M (44.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q2_K at 35.7 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 Qwerky 72B
How much VRAM does Qwerky 72B need?
About 49.8 GB at Q3_K_M with an 8K context window. That is the 44.0 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 Qwerky 72B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 40.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwerky 72B GGUF?
It depends on the quant: Q2_K is 35.7 GB, Q3_K_S is 41.5 GB, Q3_K_M is 44.0 GB, Q3_K_L is 45.1 GB, IQ4_XS is 47.8 GB.
What context length does Qwerky 72B support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download Qwerky 72B GGUF?
The files are on Hugging Face in the mradermacher/Qwerky-72B-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 Qwerky 72B 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.