Can StarCoder2 15B run on Radeon Pro W7900 48GB?

YES — Runs Great

C49Usable

○Estimated from fit model

StarCoder2 15B needs ~17.7 GB VRAM. Radeon Pro W7900 48GB has 48.0 GB. With Q5_K_M quantization, expect ~53 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) — 17.7 GB, 52.6 tok/s, Runs well

17.7 GB required48.0 GB available

37% VRAM used

Fit status

Runs well

Decode

52.6 tok/s

TTFT

3684 ms

Safe context

16K

Memory

17.7 GB / 48.0 GB

Memory breakdown

Weights10.8 GB

KV Cache1.2 GB

Runtime0.9 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsStarCoder2 15B on Radeon Pro W7900 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: 52.6 tok/s decode · 3.7s TTFT (warm) · 131 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	52.6 tok/s	2009 ms	16K
Coding	C	Runs well	52.6 tok/s	3684 ms	16K
Agentic Coding	C	Runs well	52.6 tok/s	5358 ms	16K
Reasoning	C	Runs well	52.6 tok/s	4353 ms	16K
RAG	C	Runs well	52.6 tok/s	6697 ms	16K

Quantization options

How StarCoder2 15B (15B params) fits at each quantization level on Radeon Pro W7900 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.9 GB	Low	C43
Q3_K_S	3	7.4 GB	Low	C44
NVFP4	4

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

Upgrade options