DeepSeek R1 Zero — Hardware Requirements & GPU Compatibility
ChatReasoning
DeepSeek R1 Zero is a 684.5B-parameter open language model from DeepSeek in the DeepSeek R1 family. It supports a context window of up to 163,840 tokens. At Q4_K_M it needs about 414.60 GB of VRAM — see which GPUs and Macs can run it below.
DeepSeek R1 Zero runs on a 512 GB+ Mac or a multi-GPU server
Best local pick → Mac Studio (M3 Ultra, 512GB) · Q4_K_M · 412.2 GB · ~18 tok/s
Macs from 512 GB (Q4_K_M · ~18 tok/s)
MIT
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run DeepSeek R1 Zero
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve deepseek-ai/DeepSeek-R1-Zero --max-model-len 16384 --tensor-parallel-size 8Size the nodes from the table above
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Rent 6× H100 SXM · Q4_K_M
- Estimated hourly price
- ~$16.14/hr
- est., whole server
- GPUs
- 6 GPUs
- 480 GB of VRAM
How Much VRAM Does DeepSeek R1 Zero Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 294.8 GB | 293.5 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Runs on 5× H100 SXM 80 GB | |
| 337.6 GB | 336.3 GB | 3-bit medium — 3-bit medium quantization | Runs on 5× H100 SXM 80 GB | |
| 414.6 GB | 413.3 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Runs on 6× H100 SXM 80 GB | |
| 491.6 GB | 490.3 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Runs on 7× H100 SXM 80 GB | |
| 568.6 GB | 567.3 GB | 6-bit, very good — 6-bit quantization, very good quality | Runs on 8× H100 SXM 80 GB | |
| 688.4 GB | 687.1 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Runs on 6× H200 SXM 141 GB | |
| 1372.9 GB | 1371.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on 8× B200 192 GB |
Selected Q4_K_M
4-bit medium quantization412.2GBat 16K context
- Weights
- 410.7 GB
- KV cache
- 1.2 GB
- Overhead
- 0.3 GB
Server-class: ~412.2 GB at 16K context · about 6× H100 SXM 80 GB
Which Hardware Can Run DeepSeek R1 Zero?
Q4_K_M · 414.6 GBDeepSeek R1 Zero (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 7.9 GB, bringing total usage to 422.5 GB. No consumer GPU has enough memory. 1 device with unified memory can run DeepSeek R1 Zero, including Mac Studio (M3 Ultra, 512GB).
Needs server-class hardware
DeepSeek R1 Zero runs on a 512 GB+ Mac or a multi-GPU server · Q4_K_M needs ~412.2 GB
| Hardware | Quant | Memory | Speed | Context | Hardware page | |
|---|---|---|---|---|---|---|
| Mac 512 GB · Mac Studio (M3 Ultra, 512GB) | Q4_K_M | 412.2 GB | ~18 tok/s | 160K ctx | Mac Studio → | Q4_K_M · 412.2 GB · ~18 tok/s · 160K ctx |
| 6× H100 SXM 80 GB · 480 GB | Q4_K_M | 412.2 GB | — | 160K ctx | H100 SXM → | Q4_K_M · 412.2 GB · 160K ctx |
| 4× H200 SXM 141 GB · 564 GB | Q4_K_M | 412.2 GB | — | 160K ctx | H200 SXM → | Q4_K_M · 412.2 GB · 160K ctx |
| 3× B200 192 GB · 576 GB | Q4_K_M | 412.2 GB | — | 160K ctx | B200 → | Q4_K_M · 412.2 GB · 160K ctx |
Also: Mac Studio (M3 Ultra, 512GB) · NVIDIA DGX A100 640GB · NVIDIA DGX H100
By VRAM tier · typical GPUs and Macs at Q4_K_M
Consumer GPUs (up to 32 GB) and Macs up to 256 GB: too small for this model (needs ≥ 292.4 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Alternatives to DeepSeek R1 Zero
DeepSeek R1 family · 13 models →Similar models
4| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| DeepSeek V3.2DeepSeek | 110.4 | 412.7 GB | —needs > 24 GB | same size |
| Mistral Large 3 675B Instruct 2512Mistral AI | 89.6 | 454.4 GB | —needs > 24 GB | same size |
| Cogito 671B V2.1deepcogito | — | 404.1 GB | —needs > 24 GB | same size |
| A.X K2skt | — | 444 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- DeepSeek
- Family
- DeepSeek R1
- Parameters
- 684.5B
- Active parameters
- 40.1B per token
- Architecture
- DeepseekV3ForCausalLM
- Context Length
- 163,840 tokens
- Vocabulary Size
- 129,280
- Release Date
- 2025-01-20
- License
- MIT
Frequently Asked Questions
How much VRAM does DeepSeek R1 Zero need?
DeepSeek R1 Zero requires 414.6 GB of VRAM at Q4_K_M, or 1372.9 GB at BF16. Full 164K context adds up to 7.9 GB (422.5 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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 11.8 GB (at full 164K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run DeepSeek R1 Zero?
No — DeepSeek R1 Zero requires at least 294.8 GB at Q2_K, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for DeepSeek R1 Zero?
For DeepSeek R1 Zero, Q4_K_M (414.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (491.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 294.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run DeepSeek R1 Zero on a Mac?
Yes — Mac Studio (M3 Ultra, 512GB) and above can run DeepSeek R1 Zero. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 414.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run DeepSeek R1 Zero locally?
Yes — DeepSeek R1 Zero can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of DeepSeek R1 Zero?
At Q4_K_M, the download is about 410.72 GB. The full-precision BF16 version is 1369.06 GB. The smallest option (Q2_K) is 290.93 GB.
Which GPUs can run DeepSeek R1 Zero?
No single consumer GPU has enough VRAM to run DeepSeek R1 Zero at Q4_K_M (414.6 GB). Multi-GPU or professional hardware is required.
Which devices can run DeepSeek R1 Zero?
1 device with unified memory can run DeepSeek R1 Zero at Q4_K_M (414.6 GB), including Mac Studio (M3 Ultra, 512GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.