Skip to content
localmodel.run

Text model · DeepSeek-R1

DeepSeek-R1-0528: RAM and VRAM requirements

DeepSeek-R1-0528 needs about 384.1 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~377.13 GB to download; KV cache and overhead add the rest), or about 671.3 GB at Q8_0. The lightest hardware that runs it is a high-memory machine.

DeepSeek-R1 family · 671B params (Mixture-of-Experts: activates only 37B of 671B params per token, so generation is faster than the total size suggests) · released May 2025.

Shopping for hardware? See what runs DeepSeek-R1-0528 →

License MIT · Commercial OK ↓ 206.9K/mo ♥ 2.5K on HuggingFace
Q4_K_M GGUF
377.13 GB
Q8_0 GGUF
664.3 GB
Memory @ Q4 (4k)
~384.1 GB
Context
160 k

Q4_K_M and Q8_0 are GGUF download (file) sizes. Memory @ Q4 includes the KV cache and overhead, so it runs larger than the file on disk.

Will it run on your device?

DeepSeek-R1-0528 runs on 0 of 40 tracked devices at Q4_K_M.

0 run well 0 tight fit 40 too small
Fit check Q4_K_M
No, not enough memory
needs 384.1 GB usable 10.5 GB
See the full breakdown

Memory breakdown

Weights (Q4_K_M)377.13 GB
+
KV cache (4k)6.2 GB
+
Overhead0.8 GB
=
Total384.1 GB

How context length changes it

4k context ~384.1 GB 32k context ~427.6 GB 128k context ~576.8 GB

Longer context grows the KV cache, which for DeepSeek-R1-0528 is sized by its 37B active params, not the full 671B. It needs ~384.1 GB at 4k and ~576.8 GB at 128k.

Benchmark scores

Aider polyglot · coding

#1 of 10 ranked · Percent of 225 Exercism exercises solved across six languages.

71.4%

Sourced third-party benchmarks for the full-precision DeepSeek-R1-0528, not a specific quant. See the full leaderboard.

Quantization sizes

GGUF quantson disk
Quantization Size on disk
Q2_K 281 GB est
Q3_K_M 328 GB est
Q4_K_M (default) 377.13 GB
Q5_K_M 478.1 GB est
Q6_K 550.2 GB est
Q8_0 664.3 GB
FP16 1348 GB

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run deepseek-r1:671b
llama.cpp
$ llama-cli -hf unsloth/DeepSeek-R1-0528-GGUF:Q4_K_M
LM Studio
$ lms get unsloth/DeepSeek-R1-0528-GGUF

Which devices can run DeepSeek-R1-0528?

Apple Silicon Macs

RAM-only laptops

iPhone & iPad

Android

NVIDIA GPUs

AMD GPUs

Same job, different size

Pick by what fits your memory: step down to free up VRAM, or step up if you have headroom.

Next size down Nemotron 3 Ultra 550B-A55B 550B Next size up GLM-5.2 744B

Similar models

Head-to-head

FAQ

How much VRAM or RAM does DeepSeek-R1-0528 need?

At Q4_K_M, DeepSeek-R1-0528 needs about 384.1 GB (weights ~377.13 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~671.3 GB.

What is the Q4_K_M GGUF file size of DeepSeek-R1-0528?

The Q4_K_M GGUF file is about 377.13 GB to download, and the Q8_0 GGUF is about 664.3 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~384.1 GB of memory at Q4_K_M.

Can DeepSeek-R1-0528 run on a laptop?

DeepSeek-R1-0528 is large; you need a high-memory Mac or multi-GPU setup at Q4_K_M.

Is DeepSeek-R1-0528 cheaper to run because it is a MoE model?

It is faster, not lighter. DeepSeek-R1-0528 activates only 37B of 671B params per token (so it runs quickly), but all experts must stay in memory, so it still needs memory for the full 671B.

Can I use DeepSeek-R1-0528 commercially?

Yes. DeepSeek-R1-0528 is licensed MIT, which permits commercial use.

Understand the numbers

Short guides to the ideas behind DeepSeek-R1-0528's memory and quant figures.

The May 2025 update to DeepSeek-R1 (671B MoE, 37B active). Deeper reasoning; runs only on a multi-GPU rig or a large Mac cluster.

Sources

Last validated 2026-08-03. Memory figures are estimates. See methodology.