QR

Qwerky 72B

QrwkvGGUF by mradermacherUpdated 2025-07-18
Download on Hugging Face
Parameters79.3B
Context1024K
Layers80
Architecturerwkv6qwen2
Smallest quant28.0 GB
Quick answer

Qwerky 72B needs about 43.9 GB of memory at IQ3_XXS (a 38.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 17 quants, from 28.0 GB (IQ1_S) to 49.3 GB (Q4_0).

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 17 quant files, from 28.0 GB (IQ1_S) to 49.3 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S28.0 GB 31.9 GB
Too big Get file →
IQ1_M29.4 GB 33.4 GB
Too big Get file →
IQ2_XXS31.6 GB 35.8 GB
Too big Get file →
IQ2_XS33.3 GB 37.8 GB
Too big Get file →
IQ2_S33.4 GB 37.9 GB
Too big Get file →
IQ2_M35.2 GB 39.9 GB
Too big Get file →
Q2_K35.7 GB 40.5 GB
Too big Get file →
Q2_K_S36.0 GB 40.8 GB
Too big Get file →
IQ3_XXS38.7 GB 43.9 GB
Too big Get file →
IQ3_XS40.1 GB 45.5 GB
Too big Get file →
IQ3_S41.5 GB 47.0 GB
Too big Get file →
Q3_K_S41.5 GB 47.0 GB
Too big Get file →
IQ3_M41.8 GB 47.3 GB
Too big Get file →
Q3_K_M44.0 GB 49.8 GB
Too big Get file →
Q3_K_L45.1 GB 51.1 GB
Too big Get file →
IQ4_XS47.3 GB 53.5 GB
Too big Get file →
Q4_049.3 GB 55.7 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: the best quant that fits is IQ1_S (28.0 GB file, about 31.9 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ3_M (41.8 GB file, about 47.3 GB in use).

Which Qwerky 72B quant should you choose?

IQ3_XXS (38.7 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 IQ1_S at 28.0 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

Architecturerwkv6qwen2
Parameters79.3B
Layers80
Trained context1,048,576 tokens

Source

Quantized bymradermacher
FamilyQrwkv
Licenseother
Downloads (HF)241
Last updated2025-07-18

Frequently asked questions about Qwerky 72B

How much VRAM does Qwerky 72B need?

About 43.9 GB at IQ3_XXS with an 8K context window. That is the 38.7 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 Qwerky 72B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 31.9 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: IQ1_S is 28.0 GB, IQ1_M is 29.4 GB, IQ2_XXS is 31.6 GB, IQ2_XS is 33.3 GB, IQ2_S is 33.4 GB, IQ2_M is 35.2 GB and 11 more.

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-i1-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.

Other GGUFs of QRWKV-72B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qrwkv models

All Qrwkv →

Other large models

All large models →