Skip to content

Which Model Size to Choose ​

The largest one that fits entirely in your VRAM is the one you should choose. Running entirely in VRAM is fastest; it can still run if it doesn't fit, but part of it gets pushed into memory and computed on the CPU, which is much slower.

First try it with your VRAM:

ChooseHow large a DeepSeek can your GPU run?Rough estimate; refer to ollama ps
VRAM
Model
VRAM 8 GBFits entirely at most:8b
deepseek-r1:8b ≈ 5.7 GB
$ ollama psNAME SIZE PROCESSORdeepseek-r1:8b 5.7 GB 100% GPU

deepseek-r1:8b Can be embedded entirely into 8 GB of VRAM, runs the fastest.

What You'll Be Able to Do After This Lesson ​

  • State the file sizes of each DeepSeek-R1 size
  • Pick a size based on your own VRAM
  • Use ollama ps to confirm your choice is correct

How Big Is Each Size ​

Sizes of deepseek-r1 in the Ollama model library (ollama run deepseek-r1:<尺寸>):

SizeFile SizeContext Length
1.5b1.1 GB128K
7b4.7 GB128K
8b5.2 GB128K
14b9.0 GB128K
32b20 GB128K
70b43 GB128K
671b404 GB160K

If you run ollama run deepseek-r1 without specifying a size, you get latest, whose file size is the same as 8b: 5.2 GB.

The "b" stands for billions of parameters. Generally, the larger the size, the better the answers — and the more VRAM it consumes.

  • I know how large the file is for the size I want to try

How to Tell Whether It Fits ​

Once loaded, the model uses slightly more VRAM than the file size. In our test of the 8b: the file is 5.2 GB, and ollama ps shows 5.6 GB. So as a rough rule, VRAM needs to be noticeably larger than the file. The small tool above estimates based on this.

The real answer is in the PROCESSOR column of ollama ps:

DisplayMeaning
100% GPUEntirely on the GPU, fastest
48%/52% CPU/GPU Like thisPartly in memory, partly on the GPU, slower
100% CPUEntirely in memory, computed on the CPU, slowest

If it's not 100% GPU, try one size smaller.

Look it upMy GPU is…

Click one to see.

  • I've chosen a size and checked it with ollama ps

Checkpoint ​

  • I know the file sizes of each size
  • I know VRAM needs to be noticeably larger than the file
  • I can read the PROCESSOR column to tell whether the model is entirely on the GPU

Common Misconceptions ​

Thinking bigger is always better. A large model that doesn't fit in VRAM runs much slower. Start with the largest size that fits.

You might think the R1 on this page is DeepSeek's latest model. The latest ones are the V4 / V4.1 series, but they won't fit on a home computer, and Ollama only offers the cloud version — seeCan DeepSeek V4 run locally. What can still run locally are the R1 sizes listed above.

Thinking latest is the largest version. For this model, latest has the same file size as 8b: 5.2 GB.

Next Section ​

Call a Local Model via the API.

gaodong.aiAboutPrivacyContact

Independent tutorials, not affiliated with any product mentioned. Product names and trademarks belong to their owners. Check official pages for prices and policies.