Skip to content

DeepSeek R1 0528 on Dual DGX Spark: VRAM, speed and fit

DeepSeek R1 0528 at 1.6-bit runs on the DGX Spark 128 GB with 160K of context at about 21 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on DGX Spark 128 GB · 1.6-bit (IQ1_S) · Ollama / LM Studio · Chat

GPU memory
159 GB
of 256 GB
Context
160K
auto
Speed
21 tok/s
9.3 when full
First reply
5.1 s
2K prompt

Where the memory goes

Model
131 GB
Context
10.7 GB
Overhead
1.2 GB
OS
15.4 GB
Free
97.2 GB
Memory
159 GB of 256 GB
Context
160K tokens · auto
Speed
21 tok/s · 9.3 when full
First reply
5.1 s for a 2K prompt
Running cost
$3.15/mo at home · $287/mo on a cloud 4× A40

Validation: Validated with conditions

What DeepSeek R1 0528 on Dual DGX Spark was checked against
CheckTargetResultStatus
Fits in GPU memory241 GB usable143 GB neededPass
Headroom5% free97.2 GB free (40%)Pass
Context for chat16K or more160KPass
Writing speed15 tok/s or more21 tok/sPass
First replyunder 3 s, 2K prompt5.1 sCheck

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
DeepSeek R1 0528
Parameters
685B, 40.1B active
Precision
1.6-bit (IQ1_S)
Context
160K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
DGX Spark 128 GB
GPU can use
241 GB of 256 GB

Running cost

At home
$3.15/mo
144 W at the wall
Renting instead
$287/mo
4× A40 at $2.36/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.

How to run it

llama.cpp
llama-server -hf bartowski/deepseek-ai_DeepSeek-R1-0528-GGUF
vLLM
vllm serve deepseek-ai/DeepSeek-R1-0528
MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-R1-0528-3bit

DeepSeek R1 0528 on similar machines

All machines: DeepSeek R1 0528 VRAM requirements. Everything that runs here: what can the Dual DGX Spark run?

Other models that run on Dual DGX Spark

Questions

Can DeepSeek R1 0528 run on Dual DGX Spark?

DeepSeek R1 0528 at 1.6-bit runs on the DGX Spark 128 GB with 160K of context at about 21 tokens a second.

Report VR-1K168RJ, calculated Nov 22, 2026 from published specs, not benchmarked.