Skip to content

Qwen3 VL 30B A3B Instruct on DGX Spark: VRAM, speed and fit

Qwen3 VL 30B A3B Instruct at 8-bit runs on the DGX Spark 128 GB with 256K of context at about 51 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
63.0 GB
of 128 GB
Context
256K
auto
Speed
51 tok/s
6.5 when full
First reply
0.7 s
2K prompt

Where the memory goes

Model
30.7 GB
Context
24.0 GB
Overhead
617 MB
OS
7.7 GB
Free
65.0 GB
Memory
63.0 GB of 128 GB
Context
256K tokens · auto
Speed
51 tok/s · 6.5 when full
First reply
0.7 s for a 2K prompt
Running cost
$3.15/mo at home · $117/mo on a cloud 4× RTX 2000 Ada

Validation: Validated

What Qwen3 VL 30B A3B Instruct on DGX Spark was checked against
CheckTargetResultStatus
Fits in GPU memory120 GB usable55.3 GB neededPass
Headroom5% free65.0 GB free (54%)Pass
Context for chat16K or more256KPass
Writing speed15 tok/s or more51 tok/sPass
First replyunder 3 s, 2K prompt0.7 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
Qwen3 VL 30B A3B Instruct
Parameters
31.1B, 3B active
Precision
8-bit (Q8_0)
Context
256K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
DGX Spark 128 GB
GPU can use
120 GB of 128 GB

Running cost

At home
$3.15/mo
144 W at the wall
Renting instead
$117/mo
4× RTX 2000 Ada at $0.96/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 Qwen/Qwen3-VL-30B-A3B-Instruct-GGUF
vLLM
vllm serve Qwen/Qwen3-VL-30B-A3B-Instruct

Qwen3 VL 30B A3B Instruct on similar machines

  • M5 Ultra 512 GBRuns
  • Ryzen AI Max+ 395 64 GBRuns
  • Ryzen AI Max+ 395 128 GBRuns
  • RTX SparkRuns
  • Dual DGX SparkRuns
  • DGX Station GB300Runs
  • 2× RTX PRO 6000 BlackwellRuns
  • 4× RTX PRO 6000 BlackwellRuns

All machines: Qwen3 VL 30B A3B Instruct VRAM requirements. Everything that runs here: what can the DGX Spark run?

Other models that run on DGX Spark

Questions

Can Qwen3 VL 30B A3B Instruct run on DGX Spark?

Qwen3 VL 30B A3B Instruct at 8-bit runs on the DGX Spark 128 GB with 256K of context at about 51 tokens a second.

Report VR-1VHSJI0, calculated Nov 22, 2026 from published specs, not benchmarked.