Is unified memory on NVIDIA DGX Spark 128GB as fast as VRAM for Yi Coder 9B?

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.

Can Yi Coder 9B run on NVIDIA DGX Spark 128GB?

YES — With F16

C55Usable

Estimated from fit model

Yi Coder 9B needs ~34.2 GB VRAM. NVIDIA DGX Spark 128GB has 0 MB. With F16 quantization, expect ~14 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.

Yi Coder 9B at Q4_K_M needs 8.2 GB — too much for NVIDIA DGX Spark 128GB (0.0 GB). Runs at F16 (34.2 GB) with maximum quality. 8 quantization levels fit.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 21.2 GB, 32.4 tok/s, Runs well

21.2 GB required108.8 GB available

19% VRAM used

Fit status

Runs well

Decode

32.4 tok/s

TTFT

5967 ms

Safe context

131K

Memory

21.2 GB / 108.8 GB

Memory breakdown

Weights5.5 GB

KV Cache1.5 GB

Runtime1.2 GB

Headroom13.1 GB

See how fast it feels

See how fast it feelsYi Coder 9B 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: 32.4 tok/s decode · 6.0s TTFT (warm) · 81 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	C	Runs well	32.4 tok/s	3255 ms	131K
Coding	F	Too heavy	5.4 tok/s	36049 ms	4K
Agentic Coding	B	Runs well	32.4 tok/s	8679 ms	131K
Reasoning	C	Runs well	32.4 tok/s	7052 ms	131K
RAG	B	Runs well	32.4 tok/s	10849 ms	131K

Inference speed

Yi Coder 9B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Yi Coder 9B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~126 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	126.0	Fits
RTX 4090 24GB	24 GB	Q4_K_M	126.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	126.0

Quantization options

How Yi Coder 9B (9B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	3.5 GB	Low	C51
Q3_K_S	3	4.4 GB	Low	C51
NVFP4	4

Get started

Copy-paste commands to run Yi Coder 9B on your machine.

Run

lms load Yi-Coder-9B-Chat && lms server start

Upgrade options

Hardware that runs Yi Coder 9B well

NVIDIA H200 141GBBudget pick

141 GB VRAM (+13)4800 GB/s (+4527)

Raises estimated decode speed by about 289%.126 tok/s decode

Raises estimated decode speed by about 289%.

Adds memory headroom for longer context windows and future model growth.

~$30,000 MSRP

NVIDIA H200 PCIe 141GBBest value

141 GB VRAM (+13)4800 GB/s (+4527)

Raises estimated decode speed by about 289%.126 tok/s decode

Raises estimated decode speed by about 289%.

Adds memory headroom for longer context windows and future model growth.

~$30,000 MSRP

NVIDIA B200 180GBNVIDIA upgrade

180 GB VRAM (+52)8000 GB/s (+7727)

Raises estimated decode speed by about 289%.126 tok/s decode

Raises estimated decode speed by about 289%.

Adds memory headroom for longer context windows and future model growth.

~$30,000 MSRP

Frequently asked questions

Can NVIDIA DGX Spark 128GB run Yi Coder 9B?

Yes, NVIDIA DGX Spark 128GB can run Yi Coder 9B at F16 quantization (Runs well). The recommended Q4_K_M requires 8.2 GB which exceeds available memory, but at F16 it needs only 34.2 GB. Expected decode speed: 13.5 tok/s.

How much VRAM does Yi Coder 9B need?

Yi Coder 9B (9B parameters) requires approximately 8.2 GB at Q4_K_M quantization. On NVIDIA DGX Spark 128GB, it fits at F16 using 34.2 GB.

What is the best quantization for Yi Coder 9B?

The recommended quantization is Q4_K_M, but on NVIDIA DGX Spark 128GB the best fitting quantization is F16, which uses 34.2 GB.

What speed will Yi Coder 9B run at on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Yi Coder 9B achieves approximately 13.5 tokens per second decode speed with a time-to-first-token of 14323ms using F16 quantization.

Can NVIDIA DGX Spark 128GB run Yi Coder 9B for coding?

For coding workloads, Yi Coder 9B on NVIDIA DGX Spark 128GB receives a F grade with 5.4 tok/s and 4K context.

What context window can Yi Coder 9B use on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Yi Coder 9B can safely use up to 131K tokens of context at F16 quantization. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for NVIDIA DGX Spark 128GB See all hardware for Yi Coder 9B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/yi-coder-9b-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: