QA

QAQ 32B merge2 Q5 K S

QaqGGUF by DataSoulUpdated 2025-03-13
Download on Hugging Face
Parameters32.8B
Context128K
Layers64
Architectureqwen2
Smallest quant22.6 GB
Quick answer

QAQ 32B merge2 Q5 K S needs about 25.3 GB of memory at Q5_K_S (a 22.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

QAQ 32B merge2 Q5 K S is a 32.8B-parameter Qaq model in GGUF format, quantized by DataSoul. Its trained context length is 128K tokens. The repository has 1 quant file, from 22.6 GB (Q5_K_S) to 22.6 GB (Q5_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S22.6 GB 25.3 GB
Too big Get file →

What GPU do you need for QAQ 32B merge2 Q5 K S?

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: the best quant that fits is Q5_K_S (22.6 GB file, about 25.3 GB in use).

Which QAQ 32B merge2 Q5 K S quant should you choose?

Q5_K_S (22.6 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters32.8B
Layers64
Trained context131,072 tokens
KV cache (fp16)256 KB per token

Source

Quantized byDataSoul
FamilyQaq
Downloads (HF)6
Last updated2025-03-13

Frequently asked questions about QAQ 32B merge2 Q5 K S

How much VRAM does QAQ 32B merge2 Q5 K S need?

About 25.3 GB at Q5_K_S with an 8K context window. That is the 22.6 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 QAQ 32B merge2 Q5 K S on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of QAQ 32B merge2 Q5 K S GGUF?

It depends on the quant: Q5_K_S is 22.6 GB.

What context length does QAQ 32B merge2 Q5 K S support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download QAQ 32B merge2 Q5 K S GGUF?

The files are on Hugging Face in the DataSoul/QAQ-32B-merge2-Q5_K_S-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from DataSoul

All by DataSoul →

More Qaq models

All Qaq →

Other medium models

All medium models →