32 GB VRAM (+8)1792 GB/s (+1492)
C
Raises estimated decode speed by about 516%.131.2 tok/s decode
Raises estimated decode speed by about 516%.
Adds memory headroom for longer context windows and future model growth.
~$1,999 MSRP
Can StarCoder2 15B run on NVIDIA L4 24GB?
YES — Runs Great
C50Usable
○Estimated from fit model
StarCoder2 15B needs ~14.5 GB VRAM. NVIDIA L4 24GB has 24.0 GB. With Q4_K_M quantization, expect ~21 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: 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) — 14.5 GB, 21.3 tok/s, Runs well
14.5 GB required24.0 GB available
60% VRAM used
Fit status
Runs well
Decode
21.3 tok/s
TTFT
9084 ms
Safe context
102K
Memory
14.5 GB / 24.0 GB
Memory breakdown
Weights9.2 GB
KV Cache1.8 GB
Runtime1.2 GB
Headroom2.4 GB
See how fast it feels
See how fast it feelsStarCoder2 15B on NVIDIA L4 24GB
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: 21.3 tok/s decode · 9.1s TTFT (warm) · 53 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 | 21.3 tok/s | 4955 ms | 102K |
| Coding | C | Runs well | 21.3 tok/s | 9084 ms | 102K |
| Agentic Coding | C | Runs well | 21.3 tok/s | 13214 ms | 102K |
| Reasoning | C | Runs well | 21.3 tok/s | 10736 ms | 102K |
| RAG | C | Runs well | 21.3 tok/s | 16517 ms | 102K |
Quantization options
How StarCoder2 15B (15B params) fits at each quantization level on NVIDIA L4 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | C46 |
Q3_K_S | 3 | 7.4 GB | Low | C47 |
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
32 GB VRAM (+8)896 GB/s (+596)
C
Raises estimated decode speed by about 286%.82.3 tok/s decode
Raises estimated decode speed by about 286%.
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
32 GB VRAM (+8)576 GB/s (+276)
C
Raises estimated decode speed by about 137%.50.4 tok/s decode
Raises estimated decode speed by about 137%.
Adds memory headroom for longer context windows and future model growth.
~$4,000 MSRP