Can StarCoder2 15B run on Gaudi 3 128GB?

YES — Runs Great

C48Usable

○Estimated from fit model

StarCoder2 15B needs ~25.7 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q5_K_M quantization, expect ~210 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: 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

Q5_K_M (High quality) — 25.7 GB, 210.0 tok/s, Runs well

25.7 GB required128.0 GB available

20% VRAM used

Fit status

Runs well

Decode

210.0 tok/s

TTFT

922 ms

Safe context

16K

Memory

25.7 GB / 128.0 GB

Memory breakdown

Weights10.8 GB

KV Cache1.2 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsStarCoder2 15B on Gaudi 3 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: 210.0 tok/s decode · 922ms TTFT (warm) · 525 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	210.0 tok/s	503 ms	16K
Coding	C	Runs well	210.0 tok/s	922 ms	16K
Agentic Coding	C	Runs well	210.0 tok/s	1341 ms	16K
Reasoning	C	Runs well	210.0 tok/s	1090 ms	16K
RAG	C	Runs well	210.0 tok/s	1676 ms	16K

Quantization options

How StarCoder2 15B (15B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.9 GB	Low	D40
Q3_K_S	3	7.4 GB	Low	D40
NVFP4	4	8.4 GB	Medium	D40
Q4_K_M	4	9.2 GB	Medium	D40
Q5_K_M	5	10.8 GB	High	D40
Q6_K	6	12.3 GB	High	D40
Q8_0	8	16.1 GB	Very High	C40
F16Best for your GPU	16	30.7 GB	Maximum	C42

Get started

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

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "bigcode/starcoder2-15b" \
 --hf-file "starcoder2-15b-Q5_K_M.gguf" \
 -c 4096 -ngl 99

Frequently asked questions

See all results for Gaudi 3 128GB See all hardware for StarCoder2 15B

URL: https://willitrunai.com/can-run/starcoder2-15b-on-gaudi-3-128gb