DeepSeek R1 (671B) — VRAM, Speed & Local Setup

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 20 stycznia 2025

Model library → DeepSeek R1 → DeepSeek R1 (671B)

The full massive MoE model. Requires enterprise hardware (H100/A100 clusters). State of the art.

DeepSeek R1 (671B) needs about 406 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters	671 Billion
Context window	128,000
Architecture	MoE
Provider	DeepSeek
Licence	MIT
Specified at	Q4_K_M
System RAM	700 GB
Record updated	2025-01-20

Licence

MIT — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), at 8K context. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

Quant	Weights	VRAM needed	Est. speed	Fit on 24 GB
Q2_K	220.6 GB	222.0 GB	—	Won't fit
Q3_K_M	286.0 GB	287.4 GB	—	Won't fit
Q4_K_M	405.1 GB	406.5 GB	—	Won't fit
Q5_K_M	475.6 GB	476.9 GB	—	Won't fit
Q6_K	550.2 GB	551.6 GB	—	Won't fit
Q8_0	712.9 GB	714.3 GB	—	Won't fit
F16	1342.0 GB	1343.4 GB	—	Won't fit

Want the memory numbers alone, at every quantization level and your own context length? Use the DeepSeek R1 (671B) VRAM calculator.

Buy This HardwareApple Mac Studio M3 Ultra — 512 GB VRAM · 60 W board power Deploy in the Cloud NowRunPod

or compare on Vast.ai

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Recommended GPU

The cheapest catalogued GPU that runs DeepSeek R1 (671B) is the Apple M3 Ultra (512 GB).

Ujawnienie afiliacyjne: Niektóre odnośniki na tej stronie to linki afiliacyjne — jeśli dokonasz zakupu za ich pośrednictwem, LLM Configurator może otrzymać prowizję bez dodatkowych kosztów dla Ciebie. Jako uczestnik programu Amazon Associates, LLM Configurator zarabia na kwalifikujących się zakupach.

Apple Mac Studio M3 Ultra

512 GB VRAM · 60 W board power

Ceny w 2026 są niestabilne — sprawdź aktualną ofertę.

Sprawdź cenę na Amazon

How to Run DeepSeek R1 (671B)

Install Ollama, then run:

ollama run deepseek-r1:671b

Weights on Hugging Face: deepseek-ai/DeepSeek-R1.

Best for: research, enterprise.

Can I Run DeepSeek R1 (671B) on My GPU?

Other DeepSeek R1 Sizes

DeepSeek R1 Distill Llama 8B — about 6 GB VRAM at Q4_K_M
DeepSeek R1 Distill Qwen 32B — about 20 GB VRAM at Q4_K_M
DeepSeek R1 Distill Qwen 14B — about 9 GB VRAM at Q4_K_M

DeepSeek R1 (671B) — Frequently Asked Questions

How much VRAM does DeepSeek R1 (671B) need?

About 406 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does DeepSeek R1 (671B) run on an RTX 4090 (24 GB)?

No. DeepSeek R1 (671B) needs about 406 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.

How do I run DeepSeek R1 (671B) locally?

Install Ollama and run `ollama run deepseek-r1:671b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does DeepSeek R1 come in?

DeepSeek R1 Distill Llama 8B (6 GB), DeepSeek R1 Distill Qwen 32B (20 GB), DeepSeek R1 Distill Qwen 14B (9 GB), DeepSeek R1 (671B) (406 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All DeepSeek R1 models | VRAM calculator | Check your own hardware