deepseek r1 14b needs about 11.1 GB of memory at its main file (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
DeepSeek-R1 14B: 14.8B parameter reasoning model in GGUF format
DeepSeek-R1 14B is a 14.8B parameter model based on the Qwen2 architecture. It supports reasoning and tool usage. The model was exported from Ollama and converted to GGUF, fitting on a 24GB card.
Good at
- Reasoning
- Tool usage
- Large context (131072 tokens)
Limits
- No vision support
- Requires ~11.1GB VRAM at 8k context
- MIT license only
Best for
- Complex reasoning tasks
- Tool-assisted workflows
- Long-context document analysis
Who it’s for. Researchers and developers needing a large reasoning model that can be run locally with a 24GB GPU. The model is suitable for applications that require tool integration and extended context handling.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 9.0 GB | 11.1 GB | Too big | Get file → |
The only available quant is unknown, file size 8.99GB. Estimated memory usage is 11.1GB at 8k context. For 24GB VRAM, this quant is suitable. No other quant options are provided.
What GPU do you need for deepseek r1 14b?
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: the best quant that fits is the main file (9.0 GB file, about 11.1 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about deepseek r1 14b
How much VRAM does deepseek r1 14b need?
About 11.1 GB at its main file 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 deepseek r1 14b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of deepseek r1 14b GGUF?
It depends on the quant: file is 9.0 GB.
What context length does deepseek r1 14b support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download deepseek r1 14b GGUF?
The files are on Hugging Face in the PsiPi/deepseek-r1-14b-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 deepseek r1 14b 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 DeepSeek-R1 14B on 8GB VRAM?
No. The model requires approximately 11.1GB of VRAM at 8k context, exceeding 8GB.
Does the model support vision tasks?
No. The model has no vision capabilities.