32 GB VRAM (+8)1792 GB/s (+1492)
B
Raises estimated decode speed by about 515%.151.8 tok/s decode
Raises estimated decode speed by about 515%.
Adds memory headroom for longer context windows and future model growth.
~$1,999 MSRP
Can Qwen 2.5 Coder 14B run on NVIDIA L4 24GB?
YES — Runs Great
B65Good
○Estimated from fit model
Qwen 2.5 Coder 14B needs ~15.1 GB VRAM. NVIDIA L4 24GB has 24.0 GB. With Q4_K_M quantization, expect ~25 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) — 15.1 GB, 24.7 tok/s, Runs well
15.1 GB required24.0 GB available
63% VRAM used
Fit status
Runs well
Decode
24.7 tok/s
TTFT
7851 ms
Safe context
65K
Memory
15.1 GB / 24.0 GB
Memory breakdown
Weights8.5 GB
KV Cache2.9 GB
Runtime1.2 GB
Headroom2.4 GB
See how fast it feels
See how fast it feelsQwen 2.5 Coder 14B 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: 24.7 tok/s decode · 7.9s TTFT (warm) · 62 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 | B | Runs well | 24.7 tok/s | 4282 ms | 65K |
| Coding | B | Runs well | 24.7 tok/s | 7851 ms | 65K |
| Agentic Coding | B | Runs well | 24.7 tok/s | 11419 ms | 65K |
| Reasoning | B | Runs well | 24.7 tok/s | 9278 ms | 65K |
| RAG | B | Runs well | 24.7 tok/s | 14274 ms | 65K |
Quantization options
How Qwen 2.5 Coder 14B (14B params) fits at each quantization level on NVIDIA L4 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | B60 |
Q3_K_S | 3 | 6.9 GB | Low | B61 |
NVFP4 | 4 | 7.8 GB | Medium | B61 |
Q4_K_M | 4 | 8.5 GB | Medium | B62 |
Q5_K_M | 5 | 10.1 GB | High | B63 |
Q6_K | 6 | 11.5 GB | High | B64 |
Q8_0Best for your GPU | 8 | 15.0 GB | Very High | B64 |
F16 | 16 | 28.7 GB | Maximum | F0 |
Get started
Copy-paste commands to run Qwen 2.5 Coder 14B on your machine.
Run
ollama run qwen2.5-coder:14bUpgrade options
Hardware that runs Qwen 2.5 Coder 14B well
32 GB VRAM (+8)896 GB/s (+596)
B
Raises estimated decode speed by about 285%.95.2 tok/s decode
Raises estimated decode speed by about 285%.
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
32 GB VRAM (+8)900 GB/s (+600)
B
Raises estimated decode speed by about 209%.76.3 tok/s decode
Raises estimated decode speed by about 209%.
Adds memory headroom for longer context windows and future model growth.
~$8,999 MSRP