Can StarCoder 15B run on Radeon Pro W6800 32GB?

YES — Tight Fit

A75Great

○Estimated from fit model

StarCoder 15B needs ~29.8 GB VRAM. Radeon Pro W6800 32GB has 32.0 GB. With Q5_K_M quantization, expect ~27 tok/s.

Runtime: OllamaCapacity: TightBandwidth: MediumStack: 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

Q5_K_M (High quality) — 29.8 GB, 27.1 tok/s, Tight fit

29.8 GB required32.0 GB available

93% VRAM used

Fit status

Tight fit

Decode

27.1 tok/s

TTFT

7149 ms

Safe context

Memory

29.8 GB / 32.0 GB

Memory breakdown

Weights10.8 GB

KV Cache14.6 GB

Runtime1.2 GB

Headroom3.2 GB

See how fast it feels

See how fast it feelsStarCoder 15B on Radeon Pro W6800 32GB
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: 27.1 tok/s decode · 7.1s TTFT (warm) · 68 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs well	27.1 tok/s	3900 ms	8K
Coding	A	Tight fit	27.1 tok/s	7149 ms	8K
Agentic Coding	F	Too heavy	10.1 tok/s	27754 ms	8K
Reasoning	A	Tight fit	27.1 tok/s	8449 ms	8K
RAG	F	Too heavy	10.1 tok/s	34693 ms	8K

Quantization options

How StarCoder 15B (15B params) fits at each quantization level on Radeon Pro W6800 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.9 GB	Low	B69
Q3_K_S	3	7.4 GB	Low	B70
NVFP4	4	8.4 GB	Medium	A70
Q4_K_M	4	9.2 GB	Medium	A71
Q5_K_M	5	10.8 GB	High	A71
Q6_K	6	12.3 GB	High	A72
Q8_0Best for your GPU	8	16.1 GB	Very High	A74
F16	16	30.7 GB	Maximum	F0

Get started

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

Run

lms load starcoder && lms server start

Your hardware

More models your Radeon Pro W6800 32GB can run

Model	Params	Grade	Decode
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	43.4 tok/s
👁 Alibaba Qwen 3.5 27B	27B	S	18.8 tok/s
👁 Alibaba Qwen 3.6 27B	27B	S	18.9 tok/s
👁 Alibaba Qwen 3.6 35B A3B	35B	S	36.4 tok/s
👁 Alibaba Qwen3-VL 30B A3B Instruct	30B	S	44.8 tok/s

Frequently asked questions

See all results for Radeon Pro W6800 32GB See all hardware for StarCoder 15B

URL: https://willitrunai.com/can-run/starcoder-15b-on-radeon-pro-w6800-32gb

⇱ StarCoder 15B on Radeon Pro W6800 32GB? TIGHT FIT