Will It Run AI

Can Llama 4 Scout 17B 16E run on NVIDIA DGX Spark 128GB?

YES — Runs Great

A76Great
Estimated from fit model

Llama 4 Scout 17B 16E needs ~83.7 GB VRAM. NVIDIA DGX Spark 128GB has 108.8 GB. With Q4_K_M quantization, expect ~6 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: LowStack: BasicBottleneck: Memory bandwidth
Share:

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 83.7 GB, 6.3 tok/s, Runs well
83.7 GB required108.8 GB available
77% VRAM used

Fit status

Runs well

Decode

6.3 tok/s

TTFT

30909 ms

Safe context

153K

Memory

83.7 GB / 108.8 GB

Memory breakdown

Weights66.5 GB
KV Cache2.9 GB
Runtime1.2 GB
Headroom13.1 GB

See how fast it feels

See how fast it feelsLlama 4 Scout 17B 16E on NVIDIA DGX Spark 128GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step. Given information: - Speed = 60 mph (miles per hour) - Time = 2.5 hours Formula: Distance = Speed x Time Calculation: Distance = 60 mph x 2.5 h = 150 miles The train travels 150 miles. Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time. Breakdown: - First half: 1.25 hours at 60 mph = 75 miles - Stop: 20 minutes (no distance) - Second half: 1.25 hours at 60 mph = 75 miles Total distance: 150 miles (same) Total time: 2.5 h + 0.33 h = 2.83 hours Average speed: 150 / 2.83 = 53 mph The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 6.3 tok/s decode · 30.9s TTFT (warm) · 16 tok/s prefill

What limits this setup

The model fits in shared memory, but shared-memory bandwidth is now the real limiter.

Fit does not mean dedicated-VRAM speed

Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.

Shared-memory contention still exists

The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.

Best improvement path

Prioritize bandwidth, not only capacity

If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatARuns well6.3 tok/s16859 ms153K
CodingARuns well6.3 tok/s30909 ms153K
Agentic CodingARuns well6.3 tok/s44958 ms153K
ReasoningARuns well6.3 tok/s36528 ms153K
RAGARuns well6.3 tok/s56197 ms153K

Quantization options

How Llama 4 Scout 17B 16E (109B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
42.5 GB
LowA74
Q3_K_S
3
53.4 GB
LowA76
NVFP4
4
61.0 GB
MediumA76
Q4_K_MBest for your GPU
4
66.5 GB
MediumA76
Q5_K_M
5
78.5 GB
HighF0
Q6_K
6
89.4 GB
HighF0
Q8_0
8
116.6 GB
Very HighF0
F16
16
223.5 GB
MaximumF0

Get started

Copy-paste commands to run Llama 4 Scout 17B 16E on your machine.

Run

lms load Llama-4-Scout-17B-16E-Instruct && lms server start

Your hardware

More models your NVIDIA DGX Spark 128GB can run

ModelParamsGradeDecodeCapabilities
MistralDevstral 2 123B Instruct123BS2.4 tok/s
AlibabaQwen 3.5 122B A10B122BS6.6 tok/s
MistralMistral Small 4 119B119BS7.1 tok/s
OpenAIGPT-OSS 120B117BA2.5 tok/s
CohereCommand A 111B111BS2.6 tok/s

Frequently asked questions

Can NVIDIA DGX Spark 128GB run Llama 4 Scout 17B 16E?

Yes, NVIDIA DGX Spark 128GB can run Llama 4 Scout 17B 16E with a A grade (Runs well). Expected decode speed: 6.3 tok/s.

How much VRAM does Llama 4 Scout 17B 16E need?

Llama 4 Scout 17B 16E (109B parameters) requires approximately 83.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Llama 4 Scout 17B 16E?

The recommended quantization for Llama 4 Scout 17B 16E is Q4_K_M, which balances quality and memory efficiency.

What speed will Llama 4 Scout 17B 16E run at on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Llama 4 Scout 17B 16E achieves approximately 6.3 tokens per second decode speed with a time-to-first-token of 30909ms using Q4_K_M quantization.

Can NVIDIA DGX Spark 128GB run Llama 4 Scout 17B 16E for coding?

For coding workloads, Llama 4 Scout 17B 16E on NVIDIA DGX Spark 128GB receives a A grade with 6.3 tok/s and 153K context.

What context window can Llama 4 Scout 17B 16E use on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Llama 4 Scout 17B 16E can safely use up to 153K tokens of context. The model's official context limit is 10.5M, but available memory constrains the safe maximum.

What should I upgrade first if Llama 4 Scout 17B 16E feels slow on NVIDIA DGX Spark 128GB?

Prioritize bandwidth, not only capacity. If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.

Is unified memory on NVIDIA DGX Spark 128GB as fast as VRAM for Llama 4 Scout 17B 16E?

Not always. NVIDIA DGX Spark 128GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.

See all results for NVIDIA DGX Spark 128GBSee all hardware for Llama 4 Scout 17B 16E
Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/llama-4-scout-17b-16e-on-dgx-spark-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: