QW

QwQ 44.5B

QwenGGUF by mradermacherUpdated 2025-07-31
Download on Hugging Face
Parameters44.5B
Context40K
Layers88
Architectureqwen2
Smallest quant16.6 GB
Quick answer

QwQ 44.5B needs about 30.3 GB of memory at Q4_K_M (a 26.9 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 11 quants, from 16.6 GB (Q2_K) to 47.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.

QwQ 44.5B is a 44.5B-parameter Qwen model in GGUF format, quantized by mradermacher. Its trained context length is 40K tokens. The repository has 11 quant files, from 16.6 GB (Q2_K) to 47.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K16.6 GB 20.0 GB
Too big Get file →
Q3_K_S19.4 GB 22.9 GB
Too big Get file →
Q3_K_M21.5 GB 25.0 GB
Too big Get file →
Q3_K_L23.3 GB 26.8 GB
Too big Get file →
IQ4_XS24.2 GB 27.6 GB
Too big Get file →
Q4_K_S25.4 GB 28.9 GB
Too big Get file →
Q4_K_M26.9 GB 30.3 GB
Too big Get file →
Q5_K_S30.7 GB 34.1 GB
Too big Get file →
Q5_K_M31.5 GB 35.0 GB
Too big Get file →
Q6_K36.5 GB 39.9 GB
Too big Get file →
Q8_047.3 GB 50.7 GB
Too big Get file →

What GPU do you need for QwQ 44.5B?

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 Q3_K_S (19.4 GB file, about 22.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (26.9 GB file, about 30.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (36.5 GB file, about 39.9 GB in use).

Which QwQ 44.5B quant should you choose?

Q4_K_M is the usual starting point for QwQ 44.5B: it balances file size and quality well. Here it is a 26.9 GB file.

The Q8_0 file is 47.3 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 16.6 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

Architectureqwen2
Parameters44.5B
Layers88
Trained context40,960 tokens
KV cache (fp16)352 KB per token

Source

Quantized bymradermacher
FamilyQwen
Downloads (HF)80
Last updated2025-07-31

Frequently asked questions about QwQ 44.5B

How much VRAM does QwQ 44.5B need?

About 30.3 GB at Q4_K_M with an 8K context window. That is the 26.9 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 QwQ 44.5B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of QwQ 44.5B GGUF?

It depends on the quant: Q2_K is 16.6 GB, Q3_K_S is 19.4 GB, Q3_K_M is 21.5 GB, Q3_K_L is 23.3 GB, IQ4_XS is 24.2 GB, Q4_K_S is 25.4 GB and 5 more.

What context length does QwQ 44.5B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 3.0 GB at 8K and 11.8 GB at 32K.

Where can I download QwQ 44.5B GGUF?

The files are on Hugging Face in the mradermacher/QwQ-44.5B-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 mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →