Skip to content

Qwen2.5 72B Instruct on Dual DGX Spark: VRAM, speed and fit

Qwen2.5 72B Instruct at 8-bit runs on the DGX Spark 128 GB with 32K of context at about 2.5 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on DGX Spark 128 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
98.6 GB
of 256 GB
Context
32K
auto
Speed
2.5 tok/s
Slow
First reply
2.8 s
2K prompt

Where the memory goes

Model
71.9 GB
Context
10.0 GB
Overhead
1.3 GB
OS
15.4 GB
Free
157 GB
Memory
98.6 GB of 256 GB
Context
32K tokens · auto
Speed
2.5 tok/s · slow
First reply
2.8 s for a 2K prompt
Running cost
$3.15/mo at home · $131/mo on a cloud 4× RTX A5000

Validation: Not validated

What Qwen2.5 72B Instruct on Dual DGX Spark was checked against
CheckTargetResultStatus
Fits in GPU memory241 GB usable83.3 GB neededPass
Headroom5% free157 GB free (65%)Pass
Context for chat16K or more32KPass
Writing speed15 tok/s or more2.5 tok/sFails
First replyunder 3 s, 2K prompt2.8 sPass

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
Qwen2.5 72B Instruct
Parameters
72.7B
Precision
8-bit (Q8_0)
Context
32K, 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
$131/mo
4× RTX A5000 at $1.08/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/Qwen2.5-72B-Instruct-GGUF
vLLM
vllm serve Qwen/Qwen2.5-72B-Instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen2.5-72B-Instruct-4bit

Qwen2.5 72B Instruct on similar machines

All machines: Qwen2.5 72B Instruct VRAM requirements. Everything that runs here: what can the Dual DGX Spark run?

Other models that run on Dual DGX Spark

Questions

Can Qwen2.5 72B Instruct run on Dual DGX Spark?

Qwen2.5 72B Instruct at 8-bit runs on the DGX Spark 128 GB with 32K of context at about 2.5 tokens a second.

Report VR-1EXAG8Z, calculated Nov 22, 2026 from published specs, not benchmarked.