Can Qwen 2.5 Coder 3B run on NVIDIA L4 24GB?

YES — Runs Great

A72Great

○Estimated from fit model

Qwen 2.5 Coder 3B needs ~7.3 GB VRAM. NVIDIA L4 24GB has 24.0 GB. With Q4_K_M quantization, expect ~48 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: StandardBottleneck: Balanced

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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 7.3 GB, 48.0 tok/s, Runs well

7.3 GB required24.0 GB available

30% VRAM used

Fit status

Runs well

Decode

48.0 tok/s

TTFT

4033 ms

Safe context

131K

Memory

7.3 GB / 24.0 GB

Memory breakdown

Weights1.8 GB

KV Cache2.2 GB

Runtime0.9 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsQwen 2.5 Coder 3B 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: 48.0 tok/s decode · 4.0s TTFT (warm) · 120 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	A	Runs well	48.0 tok/s	2200 ms	131K
Coding	A	Runs well	48.0 tok/s	4033 ms	131K
Agentic Coding	A	Runs well	48.0 tok/s	5867 ms	131K
Reasoning	A	Runs well	48.0 tok/s	4767 ms	131K
RAG	A	Runs well	48.0 tok/s	7333 ms	131K

Quantization options

How Qwen 2.5 Coder 3B (3B params) fits at each quantization level on NVIDIA L4 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	1.2 GB	Low	B69
Q3_K_S	3	1.5 GB	Low	B70
NVFP4	4	1.7 GB	Medium	B70
Q4_K_M	4	1.8 GB	Medium	B70
Q5_K_M	5	2.2 GB	High	B70
Q6_K	6	2.5 GB	High	B70
Q8_0	8	3.2 GB	Very High	A70
F16Best for your GPU	16	6.1 GB	Maximum	A72

Get started

Copy-paste commands to run Qwen 2.5 Coder 3B on your machine.

Run

ollama run qwen2.5-coder:3b

Your hardware

More models your NVIDIA L4 24GB can run

Model	Params	Grade	Decode
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	21.2 tok/s
👁 Alibaba Qwen 3.5 27B	27B	S	8.9 tok/s
👁 Alibaba Qwen 3.6 27B	27B	S	6.2 tok/s
👁 Alibaba Qwen 3.6 35B A3B	35B	A	13.6 tok/s
👁 Alibaba Qwen3-VL 30B A3B Instruct	30B	S	30.5 tok/s

Frequently asked questions

See all results for NVIDIA L4 24GB See all hardware for Qwen 2.5 Coder 3B

URL: https://willitrunai.com/can-run/qwen-2.5-coder-3b-on-l4-24gb

⇱ Qwen 2.5 Coder 3B on NVIDIA L4 24GB? YES