20 GB VRAM (+4)
B
Adds memory headroom for longer context windows and future model growth.35.5 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$1,250 MSRP
Can Qwen 2.5 Coder 14B run on Tesla P100 16GB?
YES — Tight Fit
B66Good
○Estimated from fit model
Qwen 2.5 Coder 14B needs ~14.3 GB VRAM. Tesla P100 16GB has 16.0 GB. With Q4_K_M quantization, expect ~51 tok/s.
Runtime: OllamaCapacity: TightBandwidth: MediumStack: 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) — 14.3 GB, 54.6 tok/s, Tight fit
14.3 GB required16.0 GB available
89% VRAM used
Fit status
Tight fit
Decode
54.6 tok/s
TTFT
3545 ms
Safe context
25K
Memory
14.3 GB / 16.0 GB
Memory breakdown
Weights8.5 GB
KV Cache2.9 GB
Runtime1.2 GB
Headroom1.6 GB
See how fast it feels
See how fast it feelsQwen 2.5 Coder 14B on Tesla P100 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: 54.6 tok/s decode · 3.5s TTFT (warm) · 137 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 54.6 tok/s | 1933 ms | 25K |
| Coding | B | Tight fit | 50.6 tok/s | 3828 ms | 25K |
| Agentic Coding | C | Runs with offload (needs ~0.6 GB host RAM) | 34.0 tok/s | 8285 ms | 25K |
| Reasoning | B | Tight fit | 54.6 tok/s | 4189 ms | 25K |
| RAG | C | Runs with offload (needs ~0.6 GB host RAM) | 34.0 tok/s | 10356 ms |
Quantization options
How Qwen 2.5 Coder 14B (14B params) fits at each quantization level on Tesla P100 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | B64 |
Q3_K_S | 3 | 6.9 GB | Low | B65 |
NVFP4 | 4 |
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
24 GB VRAM (+8)936 GB/s (+204)
B
Raises estimated decode speed by about 52%.82.9 tok/s decode
Raises estimated decode speed by about 52%.
Adds memory headroom for longer context windows and future model growth.
~$1,499 MSRP
24 GB VRAM (+8)
B
Raises estimated decode speed by about 31%.71.4 tok/s decode
Raises estimated decode speed by about 31%.
Adds memory headroom for longer context windows and future model growth.
~$1,599 MSRP