20 GB VRAM (+4)360 GB/s (+72)
C
Raises estimated decode speed by about 28%.30.7 tok/s decode
Raises estimated decode speed by about 28%.
Adds memory headroom for longer context windows and future model growth.
~$1,250 MSRP
Can StarCoder2 15B run on RTX 2000 Ada 16GB?
YES — Tight Fit
C49Usable
○Estimated from fit model
StarCoder2 15B needs ~13.7 GB VRAM. RTX 2000 Ada 16GB has 16.0 GB. With Q4_K_M quantization, expect ~24 tok/s.
Runtime: OllamaCapacity: TightBandwidth: LowStack: BasicBottleneck: 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
Q4_K_M (Medium quality) — 13.7 GB, 23.9 tok/s, Tight fit
13.7 GB required16.0 GB available
86% VRAM used
Fit status
Tight fit
Decode
23.9 tok/s
TTFT
8093 ms
Safe context
37K
Memory
13.7 GB / 16.0 GB
Memory breakdown
Weights9.2 GB
KV Cache1.8 GB
Runtime1.2 GB
Headroom1.6 GB
See how fast it feels
See how fast it feelsStarCoder2 15B on RTX 2000 Ada 16GB
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: 23.9 tok/s decode · 8.1s TTFT (warm) · 60 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 | 23.9 tok/s | 4414 ms | 37K |
| Coding | C | Tight fit | 23.9 tok/s | 8093 ms | 37K |
| Agentic Coding | C | Runs with offload | 23.9 tok/s | 11772 ms | 37K |
| Reasoning | C | Tight fit | 23.9 tok/s | 9565 ms | 37K |
| RAG | C | Runs with offload | 23.9 tok/s | 14715 ms | 37K |
Quantization options
How StarCoder2 15B (15B params) fits at each quantization level on RTX 2000 Ada 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | C50 |
Q3_K_S | 3 | 7.4 GB | Low | C51 |
NVFP4 | 4 |
Get started
Copy-paste commands to run StarCoder2 15B on your machine.
Run
lms load hf-second-state--starcoder2-15b-gguf && lms server startUpgrade options
Hardware that runs StarCoder2 15B well
24 GB VRAM (+8)936 GB/s (+648)
C
Raises estimated decode speed by about 200%.71.6 tok/s decode
Raises estimated decode speed by about 200%.
Adds memory headroom for longer context windows and future model growth.
~$1,499 MSRP
24 GB VRAM (+8)1008 GB/s (+720)
C
Raises estimated decode speed by about 250%.83.7 tok/s decode
Raises estimated decode speed by about 250%.
Adds memory headroom for longer context windows and future model growth.
~$1,599 MSRP