DE

DeepSeek R1 GGUF MTP

DeepSeekGGUF by pdelobelleUpdated 2025-03-12
Download on Hugging Face
Parameters12.5B
Context—
Layers—
Architecturellama
Smallest quant8.0 GB
Quick answer

DeepSeek R1 GGUF MTP needs about 9.5 GB of memory at Q4_K (a 8.0 GB file) with an 8K context window, so it fits on a 12 GB GPU.

DeepSeek R1 GGUF MTP is a 12.5B-parameter DeepSeek model in GGUF format, quantized by pdelobelle. The repository has 1 quant file, from 8.0 GB (Q4_K) to 8.0 GB (Q4_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K8.0 GB 9.5 GB
Too big Get file →

What GPU do you need for DeepSeek R1 GGUF MTP?

These figures add the file size, an fp16 KV cache at an 8K context window 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 Q4_K (8.0 GB file, about 9.5 GB in use).

Which DeepSeek R1 GGUF MTP quant should you choose?

Q4_K (8.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters12.5B

Source

Quantized bypdelobelle
FamilyDeepSeek
Licensemit
Downloads (HF)62
Last updated2025-03-12

Frequently asked questions about DeepSeek R1 GGUF MTP

How much VRAM does DeepSeek R1 GGUF MTP need?

About 9.5 GB at Q4_K with an 8K context window. That is the 8.0 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 GGUF MTP on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek R1 GGUF MTP GGUF?

It depends on the quant: Q4_K is 8.0 GB.

Where can I download DeepSeek R1 GGUF MTP GGUF?

The files are on Hugging Face in the pdelobelle/DeepSeek-R1-GGUF-MTP 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 GGUF MTP 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.

Other GGUFs of DeepSeek-R1

Similar models

Browse all →

More DeepSeek models

All DeepSeek →

Other medium models

All medium models →