Can Qwen 2.5 Coder 1.5B run on GTX 1650 4GB?

YES — Runs Great

A71Great

○Estimated from fit model

Qwen 2.5 Coder 1.5B needs ~2.9 GB VRAM. GTX 1650 4GB has 4.0 GB. With Q4_K_M quantization, expect ~21 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: Very lowStack: BasicBottleneck: Memory bandwidth

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) — 2.9 GB, 21.0 tok/s, Runs well

2.9 GB required4.0 GB available

73% VRAM used

Fit status

Runs well

Decode

21.0 tok/s

TTFT

9219 ms

Safe context

33K

Memory

2.9 GB / 4.0 GB

Memory breakdown

Weights0.9 GB

KV Cache0.4 GB

Runtime1.2 GB

Headroom0.4 GB

See how fast it feels

See how fast it feelsQwen 2.5 Coder 1.5B on GTX 1650 4GB
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: 21.0 tok/s decode · 9.2s TTFT (warm) · 53 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	A	Runs well	21.0 tok/s	5029 ms	33K
Coding	A	Runs well	21.0 tok/s	9219 ms	33K
Agentic Coding	B	Tight fit	21.0 tok/s	13410 ms	33K
Reasoning	A	Runs well	21.0 tok/s	10895 ms	33K
RAG	B	Tight fit	21.0 tok/s	16762 ms	33K

Quantization options

How Qwen 2.5 Coder 1.5B (1.5B params) fits at each quantization level on GTX 1650 4GB (4.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	0.6 GB	Low	A75
Q3_K_S	3	0.7 GB	Low	A75
NVFP4	4	0.8 GB	Medium	A75
Q4_K_M	4	0.9 GB	Medium	A75
Q5_K_M	5	1.1 GB	High	A74
Q6_K	6	1.2 GB	High	A74
Q8_0Best for your GPU	8	1.6 GB	Very High	A74
F16	16	3.1 GB	Maximum	F0

Get started

Copy-paste commands to run Qwen 2.5 Coder 1.5B on your machine.

Run

ollama run qwen2.5-coder:1.5b

Your hardware

More models your GTX 1650 4GB can run

Model	Params	Grade	Decode
👁 Mistral Ministral 3 3B	3B	A	25.1 tok/s
👁 Alibaba Qwen 3.5 2B	2B	B	28 tok/s
👁 Alibaba Qwen 3 1.7B	1.7B	B	23.8 tok/s

Frequently asked questions

See all results for GTX 1650 4GB See all hardware for Qwen 2.5 Coder 1.5B

URL: https://willitrunai.com/can-run/qwen-2.5-coder-1.5b-on-gtx-1650-4gb