QwQ 32B ARPO DeepSearch needs about 22.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 12.3 GB (Q2_K) to 34.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
32.8B Qwen2 model with 40960 token context
QwQ 32B ARPO DeepSearch is a 32.8B parameter Qwen2 model trained on 40960 tokens. It supports reasoning and tool usage. The model is released under the MIT license.
Good at
- reasoning
- tools
- large context
Limits
- trained_context_tokens 40960
- no vision support
- MIT license
Best for
- code generation
- data analysis
- research queries
Who it’s for. Developers and researchers who need a large language model with reasoning and tool‑use capabilities. The model is suitable for local deployment via llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.3 GB | 15.0 GB | Too big | Get file → | |
| Q3_K_S | 14.4 GB | 17.0 GB | Too big | Get file → | |
| Q3_K_M | 15.9 GB | 18.6 GB | Too big | Get file → | |
| Q3_K_L | 17.2 GB | 19.9 GB | Too big | Get file → | |
| IQ4_XS | 17.9 GB | 20.5 GB | Too big | Get file → | |
| Q4_K_S | 18.8 GB | 21.4 GB | Too big | Get file → | |
| Q4_K_M | 19.9 GB | 22.5 GB | Too big | Get file → | |
| Q5_K_S | 22.6 GB | 25.3 GB | Too big | Get file → | |
| Q5_K_M | 23.3 GB | 25.9 GB | Too big | Get file → | |
| Q6_K | 26.9 GB | 29.5 GB | Too big | Get file → | |
| Q8_0 | 34.8 GB | 37.5 GB | Too big | Get file → |
For 8 k context, Q2_K uses 15 GB memory, Q3_K_M uses 18.6 GB, and Q4_K_M uses 22.5 GB. Choose the smallest quant that fits your VRAM. Larger quants like Q5_K_M or Q6_K increase memory to 25.9 GB and 29.5 GB respectively.
What GPU do you need for QwQ 32B ARPO DeepSearch?
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: the best quant that fits is Q2_K (12.3 GB file, about 15.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (19.9 GB file, about 22.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (34.8 GB file, about 37.5 GB in use).
Which QwQ 32B ARPO DeepSearch quant should you choose?
Q4_K_M is the usual starting point for QwQ 32B ARPO DeepSearch: it balances file size and quality well. Here it is a 19.9 GB file.
The Q8_0 file is 34.8 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 12.3 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 QwQ 32B ARPO DeepSearch
How much VRAM does QwQ 32B ARPO DeepSearch need?
About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.9 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 32B ARPO DeepSearch on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of QwQ 32B ARPO DeepSearch GGUF?
It depends on the quant: Q2_K is 12.3 GB, Q3_K_S is 14.4 GB, Q3_K_M is 15.9 GB, Q3_K_L is 17.2 GB, IQ4_XS is 17.9 GB, Q4_K_S is 18.8 GB and 5 more.
What context length does QwQ 32B ARPO DeepSearch support?
The GGUF header lists a trained context length of 40,960 tokens (40K). 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 QwQ 32B ARPO DeepSearch GGUF?
The files are on Hugging Face in the mradermacher/QwQ-32B-ARPO-DeepSearch-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 QwQ 32B ARPO DeepSearch use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
No, the smallest quant requires 15 GB memory at 8 k context.
Can I use this model with llama.cpp?
Yes, the GGUF files are compatible with llama.cpp.
What license does this model use?
The model is released under the MIT license.