Can StarCoder2 15B run on NVIDIA L20 48GB?

YES — Runs Great

C48Usable

Estimated from fit model

StarCoder2 15B needs ~16.9 GB VRAM. NVIDIA L20 48GB has 48.0 GB. With Q4_K_M quantization, expect ~69 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: 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) — 16.9 GB, 68.9 tok/s, Runs well

16.9 GB required48.0 GB available

35% VRAM used

Fit status

Runs well

Decode

68.9 tok/s

TTFT

2809 ms

Safe context

299K

Memory

16.9 GB / 48.0 GB

Memory breakdown

Weights9.2 GB

KV Cache1.8 GB

Runtime1.2 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsStarCoder2 15B on NVIDIA L20 48GB
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: 68.9 tok/s decode · 2.8s TTFT (warm) · 172 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	68.9 tok/s	1532 ms	299K
Coding	C	Runs well	68.9 tok/s	2809 ms	299K
Agentic Coding	C	Runs well	68.9 tok/s	4085 ms	299K
Reasoning	C	Runs well	68.9 tok/s	3319 ms	299K
RAG	C	Runs well	68.9 tok/s	5107 ms	299K

Inference speed

StarCoder2 15B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for StarCoder2 15B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~131 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	131.2	Fits
RTX 4090 24GB	24 GB	Q4_K_M	83.7	Fits

Quantization options

How StarCoder2 15B (15B params) fits at each quantization level on NVIDIA L20 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.9 GB	Low	C42
Q3_K_S	3	7.4 GB	Low	C42
NVFP4	4

Get started

Copy-paste commands to run StarCoder2 15B on your machine.

Run

lms load hf-second-state--starcoder2-15b-gguf && lms server start

Frequently asked questions

Can NVIDIA L20 48GB run StarCoder2 15B?

Yes, NVIDIA L20 48GB can run StarCoder2 15B with a C grade (Runs well). Expected decode speed: 68.9 tok/s.

How much VRAM does StarCoder2 15B need?

StarCoder2 15B (15B parameters) requires approximately 16.9 GB of memory with Q4_K_M quantization.

What is the best quantization for StarCoder2 15B?

The recommended quantization for StarCoder2 15B is Q4_K_M, which balances quality and memory efficiency.

What speed will StarCoder2 15B run at on NVIDIA L20 48GB?

On NVIDIA L20 48GB, StarCoder2 15B achieves approximately 68.9 tokens per second decode speed with a time-to-first-token of 2809ms using Q4_K_M quantization.

Can NVIDIA L20 48GB run StarCoder2 15B for coding?

For coding workloads, StarCoder2 15B on NVIDIA L20 48GB receives a C grade with 68.9 tok/s and 299K context.

What context window can StarCoder2 15B use on NVIDIA L20 48GB?

On NVIDIA L20 48GB, StarCoder2 15B can safely use up to 299K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for NVIDIA L20 48GB See all hardware for StarCoder2 15B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-second-state--starcoder2-15b-gguf-on-l20-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: