Skip to content

Nemotron 3 Ultra 550B A55B on DGX Spark: VRAM, speed and fit

Nemotron 3 Ultra 550B A55B at 1.6-bit runs on the DGX Spark 128 GB with 256K of context at about 15 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
119 GB
of 128 GB
Context
256K
auto
Speed
15 tok/s
12 when full
First reply
13 s
2K prompt

Where the memory goes

Model
108 GB
Context
3.4 GB
Overhead
768 MB
OS
7.7 GB
Free
8.5 GB
Memory
119 GB of 128 GB
Context
256K tokens · auto
Speed
15 tok/s · 12 when full
First reply
13 s for a 2K prompt
Running cost
$3.15/mo at home · $287/mo on a cloud 4× A40

Validation: Not validated

What Nemotron 3 Ultra 550B A55B on DGX Spark was checked against
CheckTargetResultStatus
Fits in GPU memory120 GB usable112 GB neededPass
Headroom5% free8.5 GB free (7%)Pass
Context for chat16K or more256KPass
Writing speed15 tok/s or more15 tok/sCheck
First replyunder 3 s, 2K prompt13 sFails

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
Nemotron 3 Ultra 550B A55B
Parameters
561B, 55B active
Precision
1.6-bit (IQ1_S)
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
$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 unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF
vLLM
vllm serve nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
MLX (Mac)
mlx_lm.chat --model mlx-community/Nemotron-3-Ultra-550B-A55B-4bit

Nemotron 3 Ultra 550B A55B on similar machines

All machines: Nemotron 3 Ultra 550B A55B VRAM requirements. Everything that runs here: what can the DGX Spark run?

Other models that run on DGX Spark

Questions

Can Nemotron 3 Ultra 550B A55B run on DGX Spark?

Nemotron 3 Ultra 550B A55B at 1.6-bit runs on the DGX Spark 128 GB with 256K of context at about 15 tokens a second.

Report VR-0XVSPE8, calculated Nov 22, 2026 from published specs, not benchmarked.