Can StarCoder2 3B run on RTX 5090 32GB?

YES — Runs Great

C43Usable

Estimated from fit model

StarCoder2 3B needs ~6.4 GB VRAM. RTX 5090 32GB has 32.0 GB. With Q4_K_M quantization, expect ~57 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: 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) — 6.4 GB, 57.0 tok/s, Runs well

6.4 GB required32.0 GB available

20% VRAM used

Fit status

Runs well

Decode

57.0 tok/s

TTFT

3396 ms

Safe context

16K

Memory

6.4 GB / 32.0 GB

Memory breakdown

Weights1.8 GB

KV Cache0.5 GB

Runtime0.9 GB

Headroom3.2 GB

See how fast it feels

See how fast it feelsStarCoder2 3B on RTX 5090 32GB
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: 57.0 tok/s decode · 3.4s TTFT (warm) · 143 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	57.0 tok/s	1853 ms	16K
Coding	C	Runs well	57.0 tok/s	3396 ms	16K
Agentic Coding	C	Runs well	57.0 tok/s	4940 ms	16K
Reasoning	C	Runs well	57.0 tok/s	4014 ms	16K
RAG	C	Runs well	57.0 tok/s	6175 ms	16K

Quantization options

How StarCoder2 3B (3B params) fits at each quantization level on RTX 5090 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	1.2 GB	Low	C41
Q3_K_S	3	1.5 GB	Low	C41
NVFP4	4	1.7 GB	Medium	C41
Q4_K_M	4	1.8 GB	Medium	C41
Q5_K_M	5	2.2 GB	High	C41
Q6_K	6	2.5 GB	High	C41
Q8_0	8	3.2 GB	Very High	C42
F16Best for your GPU	16	6.1 GB	Maximum	C43

Get started

Copy-paste commands to run StarCoder2 3B on your machine.

Run

ollama run starcoder2:3b

Frequently asked questions

Can RTX 5090 32GB run StarCoder2 3B?

Yes, RTX 5090 32GB can run StarCoder2 3B with a C grade (Runs well). Expected decode speed: 57.0 tok/s.

How much VRAM does StarCoder2 3B need?

StarCoder2 3B (3B parameters) requires approximately 6.4 GB of memory with Q4_K_M quantization.

What is the best quantization for StarCoder2 3B?

The recommended quantization for StarCoder2 3B is Q4_K_M, which balances quality and memory efficiency.

What speed will StarCoder2 3B run at on RTX 5090 32GB?

On RTX 5090 32GB, StarCoder2 3B achieves approximately 57.0 tokens per second decode speed with a time-to-first-token of 3396ms using Q4_K_M quantization.

Can RTX 5090 32GB run StarCoder2 3B for coding?

For coding workloads, StarCoder2 3B on RTX 5090 32GB receives a C grade with 57.0 tok/s and 16K context.

What context window can StarCoder2 3B use on RTX 5090 32GB?

On RTX 5090 32GB, StarCoder2 3B can safely use up to 16K tokens of context. The model's official context limit is 16K, but available memory constrains the safe maximum.

See all results for RTX 5090 32GB See all hardware for StarCoder2 3B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/starcoder2-3b-on-rtx-5090-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

57.0 tok/s

1853 ms

16K

Coding

Runs well

57.0 tok/s

3396 ms

16K

Agentic Coding

Runs well

57.0 tok/s

4940 ms

16K

Reasoning

Runs well

57.0 tok/s

4014 ms

16K

RAG

Runs well

57.0 tok/s

6175 ms

16K

Quant

Bits

VRAM

Quality

Fit

Q2_K

1.2 GB

Low

C41

Q3_K_S

1.5 GB

Low

C41

NVFP4

1.7 GB

Medium

C41

Q4_K_M

1.8 GB

Medium

C41

Q5_K_M

2.2 GB

High

C41

Q6_K

2.5 GB

High

C41

Q8_0

3.2 GB

Very High

C42

F16Best for your GPU

6.1 GB

Maximum

C43

Frequently asked questions

Can RTX 5090 32GB run StarCoder2 3B?

Yes, RTX 5090 32GB can run StarCoder2 3B with a C grade (Runs well). Expected decode speed: 57.0 tok/s.

How much VRAM does StarCoder2 3B need?

StarCoder2 3B (3B parameters) requires approximately 6.4 GB of memory with Q4_K_M quantization.

What is the best quantization for StarCoder2 3B?

The recommended quantization for StarCoder2 3B is Q4_K_M, which balances quality and memory efficiency.

What speed will StarCoder2 3B run at on RTX 5090 32GB?

On RTX 5090 32GB, StarCoder2 3B achieves approximately 57.0 tokens per second decode speed with a time-to-first-token of 3396ms using Q4_K_M quantization.

Can RTX 5090 32GB run StarCoder2 3B for coding?

For coding workloads, StarCoder2 3B on RTX 5090 32GB receives a C grade with 57.0 tok/s and 16K context.

What context window can StarCoder2 3B use on RTX 5090 32GB?

On RTX 5090 32GB, StarCoder2 3B can safely use up to 16K tokens of context. The model's official context limit is 16K, but available memory constrains the safe maximum.