Can StarCoder2 15B run on NVIDIA A100 40GB?

YES — Runs Great

C50Usable

Estimated from fit model

StarCoder2 15B needs ~16.1 GB VRAM. NVIDIA A100 40GB has 40.0 GB. With Q4_K_M quantization, expect ~143 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) — 16.1 GB, 142.8 tok/s, Runs well

16.1 GB required40.0 GB available

40% VRAM used

Fit status

Runs well

Decode

142.8 tok/s

TTFT

1356 ms

Safe context

233K

Memory

16.1 GB / 40.0 GB

Memory breakdown

Weights9.2 GB

KV Cache1.8 GB

Runtime1.2 GB

Headroom4.0 GB

See how fast it feels

See how fast it feelsStarCoder2 15B on NVIDIA A100 40GB
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: 142.8 tok/s decode · 1.4s TTFT (warm) · 357 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	142.8 tok/s	740 ms	233K
Coding	C	Runs well	142.8 tok/s	1356 ms	233K
Agentic Coding	C	Runs well	142.8 tok/s	1973 ms	233K
Reasoning	C	Runs well	142.8 tok/s	1603 ms	233K
RAG	C	Runs well	142.8 tok/s	2466 ms	233K

Quantization options

How StarCoder2 15B (15B params) fits at each quantization level on NVIDIA A100 40GB (40.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.9 GB	Low	C43
Q3_K_S	3	7.4 GB	Low	C43
NVFP4	4	8.4 GB	Medium	C43
Q4_K_M	4	9.2 GB	Medium	C44
Q5_K_M	5	10.8 GB	High	C44
Q6_K	6	12.3 GB	High	C45
Q8_0	8	16.1 GB	Very High	C46
F16Best for your GPU	16	30.7 GB	Maximum	C48

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 A100 40GB run StarCoder2 15B?

Yes, NVIDIA A100 40GB can run StarCoder2 15B with a C grade (Runs well). Expected decode speed: 142.8 tok/s.

How much VRAM does StarCoder2 15B need?

StarCoder2 15B (15B parameters) requires approximately 16.1 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 A100 40GB?

On NVIDIA A100 40GB, StarCoder2 15B achieves approximately 142.8 tokens per second decode speed with a time-to-first-token of 1356ms using Q4_K_M quantization.

Can NVIDIA A100 40GB run StarCoder2 15B for coding?

For coding workloads, StarCoder2 15B on NVIDIA A100 40GB receives a C grade with 142.8 tok/s and 233K context.

What context window can StarCoder2 15B use on NVIDIA A100 40GB?

On NVIDIA A100 40GB, StarCoder2 15B can safely use up to 233K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for NVIDIA A100 40GB 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-a100-40gb" 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

142.8 tok/s

740 ms

233K

Coding

Runs well

142.8 tok/s

1356 ms

233K

Agentic Coding

Runs well

142.8 tok/s

1973 ms

233K

Reasoning

Runs well

142.8 tok/s

1603 ms

233K

RAG

Runs well

142.8 tok/s

2466 ms

233K

Quantization options

How StarCoder2 15B (15B params) fits at each quantization level on NVIDIA A100 40GB (40.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.9 GB	Low	C43
Q3_K_S	3	7.4 GB	Low	C43
NVFP4	4	8.4 GB	Medium	C43
Q4_K_M	4	9.2 GB	Medium	C44
Q5_K_M	5	10.8 GB	High	C44
Q6_K	6	12.3 GB	High	C45
Q8_0	8	16.1 GB	Very High	C46
F16Best for your GPU	16	30.7 GB	Maximum	C48

Frequently asked questions

Can NVIDIA A100 40GB run StarCoder2 15B?

Yes, NVIDIA A100 40GB can run StarCoder2 15B with a C grade (Runs well). Expected decode speed: 142.8 tok/s.

How much VRAM does StarCoder2 15B need?

StarCoder2 15B (15B parameters) requires approximately 16.1 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 A100 40GB?

On NVIDIA A100 40GB, StarCoder2 15B achieves approximately 142.8 tokens per second decode speed with a time-to-first-token of 1356ms using Q4_K_M quantization.

Can NVIDIA A100 40GB run StarCoder2 15B for coding?

For coding workloads, StarCoder2 15B on NVIDIA A100 40GB receives a C grade with 142.8 tok/s and 233K context.

What context window can StarCoder2 15B use on NVIDIA A100 40GB?

On NVIDIA A100 40GB, StarCoder2 15B can safely use up to 233K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.