Reasoning

What GPU do I need to run deepseek-ai/DeepSeek-R1-0528?

A 685B-parameter reasoning model tuned for math, coding and multi-step logic. 684.5B parameters, published in F8_E4M3. View on Hugging Face

684.5B
Parameters
F8_E4M3
Native precision
160K tokens (163,840)
Context length
MIT
License
Text
Modality
DeepSeek
Organization

DeepSeek-R1-0528 is published by deepseek-ai on Hugging Face, with 204,228 downloads and 2,459 likes to date. It's a DeepseekV3ForCausalLM model built for text-generation, published natively in F8_E4M3.

What DeepSeek-R1-0528 is

DeepSeek-R1-0528 is DeepSeek's reasoning-focused language model: it works through a problem step by step before producing a final answer, rather than answering directly. DeepSeek's own card reports a jump to 87.5% on AIME 2025 (up from 70% on the prior release) along with stronger coding and function-calling results.

License note: permissive: DeepSeek's card states it supports commercial use and distillation into other models. Facts in this section are sourced from DeepSeek-R1-0528's Hugging Face model card, not benchmarked by Aquanode.

What it's used for

  • Multi-step reasoning and math
  • Code generation
  • Function calling / tool use
  • Long-context analysis

VRAM required & cheapest live GPU fit

Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP8 (native)637.5 GB765.0 GBAMD MI300X4$10.52/hr
INT4 (quantized)318.8 GB382.5 GBRTX A60008$2.90/hr

A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.

INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.

Cheapest way to run DeepSeek-R1-0528 at its published (F8_E4M3) precision: 4× AMD MI300X, at $2.63/hr per GPU ($10.52/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.

DeepSeek-R1-0528: KV cache by context length

The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.

Multi-head latent attention: every layer caches one compressed latent per token. Cached per token: 70,272 bytes at 16-bit.

ContextKV cache, one sequence
4K0.27 GB
32K2.1 GB
128K8.6 GB
160K (model maximum)10.7 GB

Computed from the layer, head and window counts in the model's own configuration (deepseek-ai/DeepSeek-R1-0528), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.

DeepSeek-R1-0528: common questions

Can DeepSeek-R1-0528 run on a single GPU?

No. At FP8 (native) it needs 765.0 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 192.0 GB AMD MI300X, and it takes 4 of them.

Is DeepSeek-R1-0528 already quantized?

Yes. It is published in FP8, one byte per parameter, so the 765.0 GB figure is already a quantized footprint rather than a full-precision one. Only INT4 goes below it, at 382.5 GB. A GPU without FP8 tensor cores cannot run it as published, which is why cards here are matched on precision support and not on VRAM alone.

How many GPUs do I need to run DeepSeek-R1-0528?

4 at FP8 (native). It needs 765.0 GB of VRAM and the cheapest capable live offer is a 192.0 GB AMD MI300X, so 4 of them come to $10.52/hr in total.

Does quantizing DeepSeek-R1-0528 lower the GPU bill?

Yes. At FP8 (native) the cheapest live fit is 4 AMD MI300X cards at $10.52/hr. At INT4 (quantized) it drops to 8 RTX A6000 cards at $2.90/hr, provided a quantized checkpoint exists for it.

How to run DeepSeek-R1-0528

Run DeepSeek-R1-0528 with vLLM

Generic example, not from the model's own docs: adjust flags (quantization, context length, parallelism) for your setup.

vllm serve deepseek-ai/DeepSeek-R1-0528 --tensor-parallel-size 4

Run DeepSeek-R1-0528 with GGUF quantizations

Prebuilt GGUF weights published at unsloth/DeepSeek-R1-0528-GGUF. Run with llama.cpp's llama-server or load the repo directly in LM Studio.

llama-server -hf unsloth/DeepSeek-R1-0528-GGUF

Source: https://huggingface.co/unsloth/DeepSeek-R1-0528-GGUF

Deploy DeepSeek-R1-0528 on Aquanode

Aquanode has no one-click deploy template for DeepSeek-R1-0528; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.

  1. Launch a bare GPU pod sized to the requirement above (4× AMD MI300X or larger).
  2. Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
  3. Run the command and connect to the resulting endpoint.
Launch a GPU pod

Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.

More DeepSeek R1 models

All 14 DeepSeek R1 models: VRAM and GPU requirements

Alternatives at this size

Other models for text-generation within about a third of DeepSeek-R1-0528's 684.5B parameters, from other model lines.

More on DeepSeek-R1-0528

Related reading: AMD MI300X pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.

Related on Aquanode: GPU requirements for Seed-OSS-36B-Instruct, GPU requirements for Solar-Open-100B, GPU requirements for transformer-1.3B-100B, and GPU requirements for pythia-1.4b-deduped.

Your own GPU cloud accounts

One console for the GPU clouds you already rent from. Your keys stay on your machine.

$20 a month, flat

Connect your accounts

One console for the GPU clouds you already use.

Connect your accounts for $20 a month, flat. Your provider bills the GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.