Qwen3 14B ARPO DeepSearch needs about 10.8 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 5.8 GB (Q2_K) to 15.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Qwen3 14B ARPO DeepSearch – a 14.8B parameter LLM focused on reasoning and tool use
Qwen3 14B ARPO DeepSearch is a 14.8B parameter model trained with a 40960 token context window. It excels at multi‑turn reasoning and tool‑based interactions. The model is released under the MIT license.
Good at
- Multi‑turn reasoning
- Tool‑based problem solving
- Large context handling
Limits
- No vision support
- Requires 40960 token context
- No mixture of experts
Best for
- Complex reasoning tasks
- Tool‑enabled agent development
- Long‑form content generation
Who it’s for. Developers building agentic applications that need deep reasoning and tool integration. Researchers exploring reinforcement learning for LLMs may also find this model useful.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 5.8 GB | 7.6 GB | Tight | Get file → | |
| Q3_K_S | 6.7 GB | 8.5 GB | Too big | Get file → | |
| Q3_K_M | 7.3 GB | 9.2 GB | Too big | Get file → | |
| Q3_K_L | 7.9 GB | 9.7 GB | Too big | Get file → | |
| IQ4_XS | 8.2 GB | 10.0 GB | Too big | Get file → | |
| Q4_K_S | 8.6 GB | 10.4 GB | Too big | Get file → | |
| Q4_K_M | 9.0 GB | 10.8 GB | Too big | Get file → | |
| Q5_K_S | 10.3 GB | 12.1 GB | Too big | Get file → | |
| Q5_K_M | 10.5 GB | 12.4 GB | Too big | Get file → | |
| Q6_K | 12.1 GB | 14.0 GB | Too big | Get file → | |
| Q8_0 | 15.7 GB | 17.5 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (file size 5.75 GB, estimated 7.6 GB memory). For 12 GB VRAM use Q4_K_S (file size 8.57 GB, estimated 10.4 GB memory). For 16 GB VRAM use Q6_K (file size 12.12 GB, estimated 14 GB memory). These estimates are approximate.
What GPU do you need for Qwen3 14B 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: the best quant that fits is Q2_K (5.8 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (9.0 GB file, about 10.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.1 GB file, about 14.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (15.7 GB file, about 17.5 GB in use).
Which Qwen3 14B ARPO DeepSearch quant should you choose?
Q4_K_M is the usual starting point for Qwen3 14B ARPO DeepSearch: it balances file size and quality well. Here it is a 9.0 GB file.
The Q8_0 file is 15.7 GB, about 1.7 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 5.8 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 Qwen3 14B ARPO DeepSearch
How much VRAM does Qwen3 14B ARPO DeepSearch need?
About 10.8 GB at Q4_K_M with an 8K context window. That is the 9.0 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 Qwen3 14B ARPO DeepSearch on an 8 GB GPU?
Yes, with Q2_K: the 5.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3 14B ARPO DeepSearch GGUF?
It depends on the quant: Q2_K is 5.8 GB, Q3_K_S is 6.7 GB, Q3_K_M is 7.3 GB, Q3_K_L is 7.9 GB, IQ4_XS is 8.2 GB, Q4_K_S is 8.6 GB and 5 more.
What context length does Qwen3 14B 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 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Qwen3 14B ARPO DeepSearch GGUF?
The files are on Hugging Face in the mradermacher/Qwen3-14B-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 Qwen3 14B 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?
Yes, by using the Q2_K quant which requires about 7.6 GB of VRAM at 8 k context.
What is the maximum context length?
The model supports up to 40960 tokens of context.
Does it support vision?
No, the model has no vision capabilities.