40 GB VRAM (+8)1555 GB/s (+915)
C
Raises estimated decode speed by about 246%.134.7 tok/s decode
Raises estimated decode speed by about 246%.
Adds memory headroom for longer context windows and future model growth.
~$10,000 MSRP
Can StarCoder2 15B run on Radeon AI PRO R9700 32GB?
YES — Runs Great
C51Usable
○Estimated from fit model
StarCoder2 15B needs ~16.1 GB VRAM. Radeon AI PRO R9700 32GB has 32.0 GB. With Q5_K_M quantization, expect ~39 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: MediumStack: StandardBottleneck: Balanced
Share:
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.
Select quantization to explore
Q5_K_M (High quality) — 16.1 GB, 38.9 tok/s, Runs well
16.1 GB required32.0 GB available
50% VRAM used
Fit status
Runs well
Decode
38.9 tok/s
TTFT
4973 ms
Safe context
16K
Memory
16.1 GB / 32.0 GB
Memory breakdown
Weights10.8 GB
KV Cache1.2 GB
Runtime0.9 GB
Headroom3.2 GB
See how fast it feels
See how fast it feelsStarCoder2 15B on Radeon AI PRO R9700 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: 38.9 tok/s decode · 5.0s TTFT (warm) · 97 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 | 38.9 tok/s | 2712 ms | 16K |
| Coding | C | Runs well | 38.9 tok/s | 4973 ms | 16K |
| Agentic Coding | C | Runs well | 38.9 tok/s | 7233 ms | 16K |
| Reasoning | C | Runs well | 38.9 tok/s | 5877 ms | 16K |
| RAG | C | Runs well | 38.9 tok/s | 9042 ms | 16K |
Quantization options
How StarCoder2 15B (15B params) fits at each quantization level on Radeon AI PRO R9700 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | C45 |
Q3_K_S | 3 | 7.4 GB | Low | C46 |
NVFP4 | 4 | 8.4 GB | Medium | C46 |
Q4_K_M | 4 | 9.2 GB | Medium | C47 |
Q5_K_M | 5 | 10.8 GB | High | C48 |
Q6_K | 6 | 12.3 GB | High | C48 |
Q8_0Best for your GPU | 8 | 16.1 GB | Very High | C50 |
F16 | 16 | 30.7 GB | Maximum | F0 |
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 99Upgrade options