Can DeepSeek Coder V2 16B run on NVIDIA DGX Spark 128GB?

YES — Runs Great

A73Great

Estimated from fit model

DeepSeek Coder V2 16B needs ~27.3 GB VRAM. NVIDIA DGX Spark 128GB has 108.8 GB. With Q4_K_M quantization, expect ~40 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: LowStack: BasicBottleneck: Balanced

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) — 27.3 GB, 40.0 tok/s, Runs well

27.3 GB required108.8 GB available

25% VRAM used

Fit status

Runs well

Decode

40.0 tok/s

TTFT

4845 ms

Safe context

131K

Memory

27.3 GB / 108.8 GB

Memory breakdown

Weights9.8 GB

KV Cache3.3 GB

Runtime1.2 GB

Headroom13.1 GB

See how fast it feels

See how fast it feelsDeepSeek Coder V2 16B on NVIDIA DGX Spark 128GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:

def quicksort(arr):
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers))  # [1, 1, 2, 3, 6, 8, 10]

The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
    """Sort a list using the quicksort algorithm.

    Args:
        arr: List of integers to sort.

    Returns:
        A new sorted list.
    """
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 40.0 tok/s decode · 4.8s TTFT (warm) · 100 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

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

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs well	40.0 tok/s	2643 ms	131K
Coding	A	Runs well	40.0 tok/s	4845 ms	131K
Agentic Coding	A	Runs well	40.0 tok/s	7047 ms	131K
Reasoning	A	Runs well	40.0 tok/s	5726 ms	131K
RAG	A	Runs well	40.0 tok/s	8809 ms	131K

Quantization options

How DeepSeek Coder V2 16B (16B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	6.2 GB	Low	B68
Q3_K_S	3	7.8 GB	Low	B68
NVFP4	4	9.0 GB	Medium	B68
Q4_K_M	4	9.8 GB	Medium	B68
Q5_K_M	5	11.5 GB	High	B68
Q6_K	6	13.1 GB	High	B68
Q8_0	8	17.1 GB	Very High	B69
F16Best for your GPU	16	32.8 GB	Maximum	A72

Get started

Copy-paste commands to run DeepSeek Coder V2 16B on your machine.

Run

lms load DeepSeek-Coder-V2-Lite-Instruct && lms server start

Your hardware

More models your NVIDIA DGX Spark 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	2.4 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	24.8 tok/s
Qwen 3.5 27B	27B	A	10.7 tok/s
Qwen 3.6 27B	27B	A	10.8 tok/s
Qwen 3.5 122B A10B	122B	S	6.6 tok/s

Frequently asked questions

Can NVIDIA DGX Spark 128GB run DeepSeek Coder V2 16B?

Yes, NVIDIA DGX Spark 128GB can run DeepSeek Coder V2 16B with a A grade (Runs well). Expected decode speed: 40.0 tok/s.

How much VRAM does DeepSeek Coder V2 16B need?

DeepSeek Coder V2 16B (16B parameters) requires approximately 27.3 GB of memory with Q4_K_M quantization.

What is the best quantization for DeepSeek Coder V2 16B?

The recommended quantization for DeepSeek Coder V2 16B is Q4_K_M, which balances quality and memory efficiency.

What speed will DeepSeek Coder V2 16B run at on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, DeepSeek Coder V2 16B achieves approximately 40.0 tokens per second decode speed with a time-to-first-token of 4845ms using Q4_K_M quantization.

Can NVIDIA DGX Spark 128GB run DeepSeek Coder V2 16B for coding?

For coding workloads, DeepSeek Coder V2 16B on NVIDIA DGX Spark 128GB receives a A grade with 40.0 tok/s and 131K context.

What context window can DeepSeek Coder V2 16B use on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, DeepSeek Coder V2 16B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

Is unified memory on NVIDIA DGX Spark 128GB as fast as VRAM for DeepSeek Coder V2 16B?

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 128GB See all hardware for DeepSeek Coder V2 16B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/deepseek-coder-v2-16b-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:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

40.0 tok/s

2643 ms

131K

Coding

Runs well

40.0 tok/s

4845 ms

131K

Agentic Coding

Runs well

40.0 tok/s

7047 ms

131K

Reasoning

Runs well

40.0 tok/s

5726 ms

131K

RAG

Runs well

40.0 tok/s

8809 ms

131K

Quantization options

How DeepSeek Coder V2 16B (16B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	6.2 GB	Low	B68
Q3_K_S	3	7.8 GB	Low	B68
NVFP4	4	9.0 GB	Medium	B68
Q4_K_M	4	9.8 GB	Medium	B68
Q5_K_M	5	11.5 GB	High	B68
Q6_K	6	13.1 GB	High	B68
Q8_0	8	17.1 GB	Very High	B69
F16Best for your GPU	16	32.8 GB	Maximum	A72

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

2.4 tok/s

Qwen3-Coder 30B A3B Instruct

30.5B

24.8 tok/s

Qwen 3.5 27B

27B

10.7 tok/s

Qwen 3.6 27B

27B

10.8 tok/s

Qwen 3.5 122B A10B

122B

6.6 tok/s