Can NVIDIA GeForce RTX 5090 run DeepSeek R1 0528?

No — DeepSeek R1 0528 requires at least 192.1 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.

What's the best quantization for DeepSeek R1 0528?

For DeepSeek R1 0528, Q4_K_M (414.6 GB) offers the best balance of quality and VRAM usage. Q5_K_S (474.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 192.1 GB.

Can I run DeepSeek R1 0528 on a Mac?

DeepSeek R1 0528 requires at least 192.1 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.

Can I run DeepSeek R1 0528 locally?

Yes — DeepSeek R1 0528 can run locally on consumer hardware. At Q4_K_M quantization it needs 414.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.

What's the download size of DeepSeek R1 0528?

At Q4_K_M, the download is about 410.72 GB. The full-precision Q8_0 version is 684.53 GB. The smallest option (IQ2_XXS) is 188.25 GB.

DeepSeek·DeepSeek R1·DeepseekV3ForCausalLM

DeepSeek R1 0528 — Hardware Requirements & GPU Compatibility

ChatReasoning

DeepSeek R1 0528 is an updated release of the R1 reasoning model, incorporating improvements to training and inference that sharpen its performance on complex multi-step problems. It retains the same 684.5 billion parameter mixture-of-experts architecture as the original R1, with approximately 37 billion parameters active per forward pass. This revision addresses several edge cases where the original R1 struggled, delivering more consistent reasoning chains and fewer hallucinations on difficult math and coding tasks. Hardware requirements remain identical to the original R1, so users already set up to run the first version can swap in the 0528 weights with no changes to their infrastructure.

1.1M downloads 2.4K likesMay 2025164K context

Specifications

Publisher: DeepSeek
Family: DeepSeek R1
Parameters: 684.5B
Architecture: DeepseekV3ForCausalLM
Context Length: 163,840 tokens
Vocabulary Size: 129,280
Release Date: 2025-05-29
License: MIT

Get Started

HuggingFace

deepseek-ai/DeepSeek-R1-0528

How Much VRAM Does DeepSeek R1 0528 Need?

Select a quantization to see compatible GPUs below.

Quantization	Bits	VRAM	+ Context	File Size	Quality
IQ2_XXS	2.20	192.1 GB	475.1 GB	188.25 GB	Importance-weighted 2-bit, extreme compression — significant quality loss
IQ2_M	2.70	234.9 GB	517.9 GB	231.03 GB	Importance-weighted 2-bit, medium
IQ3_XXS	3.10	269.1 GB	552.1 GB	265.26 GB	Importance-weighted 3-bit
Q2_K	3.40	294.8 GB	577.8 GB	290.93 GB	2-bit quantization with K-quant improvements
Q3_K_S	3.50	303.4 GB	586.3 GB	299.48 GB	3-bit small quantization
Q3_K_M	3.90	337.6 GB	620.6 GB	333.71 GB	3-bit medium quantization
Q4_0	4.00	346.1 GB	629.1 GB	342.27 GB	4-bit legacy quantization
IQ4_XS	4.30	371.8 GB	654.8 GB	367.94 GB	Importance-weighted 4-bit, compact
Q4_1	4.50	388.9 GB	671.9 GB	385.05 GB	4-bit legacy quantization with offset
Q4_K_S	4.50	388.9 GB	671.9 GB	385.05 GB	4-bit small quantization
IQ4_NL	4.50	388.9 GB	671.9 GB	385.05 GB	Importance-weighted 4-bit, non-linear
Q4_K_M	4.80	414.6 GB	697.6 GB	410.72 GB	4-bit medium quantization — most popular sweet spot
Q5_K_S	5.50	474.5 GB	757.5 GB	470.62 GB	5-bit small quantization
Q5_K_M	5.70	491.6 GB	774.6 GB	487.73 GB	5-bit medium quantization — good quality/size tradeoff
Q6_K	6.60	568.6 GB	851.6 GB	564.74 GB	6-bit quantization, very good quality
Q8_0	8.00	688.4 GB	971.4 GB	684.53 GB	8-bit quantization, near-lossless

Which GPUs Can Run DeepSeek R1 0528?

Q4_K_M · 414.6 GB

Show professional

DeepSeek R1 0528 (Q4_K_M) requires 414.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 539+ GB is recommended. Using the full 164K context window can add up to 283.0 GB, bringing total usage to 697.6 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.

Which Devices Can Run DeepSeek R1 0528?

Q4_K_M · 414.6 GB

2 devices with unified memory can run DeepSeek R1 0528, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.

Runs great

— Plenty of headroom

NVIDIA DGX H100~42 tok/s NVIDIA DGX A100 640GB~26 tok/s

Related Models

Derivatives (1)

DeepSeek R1 0528 NVFP4 v2

Frequently Asked Questions

How much VRAM does DeepSeek R1 0528 need?: DeepSeek R1 0528 requires 414.6 GB of VRAM at Q4_K_M, or 688.4 GB at Q8_0. Full 164K context adds up to 283.0 GB (697.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 684.5B × 4.8 bits ÷ 8 = 410.7 GB
KV Cache + Overhead ≈ 3.9 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 286.9 GB (at full 164K context)
VRAM usage by quantization
Q4_K_M
414.6 GB
Q4_K_M + full context
697.6 GB
Learn more about VRAM estimation →
Can NVIDIA GeForce RTX 5090 run DeepSeek R1 0528?: No — DeepSeek R1 0528 requires at least 192.1 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for DeepSeek R1 0528?: For DeepSeek R1 0528, Q4_K_M (414.6 GB) offers the best balance of quality and VRAM usage. Q5_K_S (474.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 192.1 GB.
VRAM requirement by quantization
IQ2_XXS
192.1 GB~53%
Q3_K_S
303.4 GB~77%
Q4_1
388.9 GB~88%
Q4_K_M ★
414.6 GB~89%
Q5_K_S
474.5 GB~92%
Q8_0
688.4 GB~99%
★ Recommended — best balance of quality and VRAM usage.
Learn more about quantization →
Can I run DeepSeek R1 0528 on a Mac?: DeepSeek R1 0528 requires at least 192.1 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
Can I run DeepSeek R1 0528 locally?: Yes — DeepSeek R1 0528 can run locally on consumer hardware. At Q4_K_M quantization it needs 414.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of DeepSeek R1 0528?: At Q4_K_M, the download is about 410.72 GB. The full-precision Q8_0 version is 684.53 GB. The smallest option (IQ2_XXS) is 188.25 GB.