Can Granite Code 20B run on Tesla P40 24GB?

YES — Runs Great

A81Great

Estimated from fit model

Granite Code 20B needs ~19.0 GB VRAM. Tesla P40 24GB has 24.0 GB. With Q4_K_M quantization, expect ~18 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: LowStack: BasicBottleneck: 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) — 19.0 GB, 18.1 tok/s, Runs well

19.0 GB required24.0 GB available

79% VRAM used

Fit status

Runs well

Decode

18.1 tok/s

TTFT

10713 ms

Safe context

Memory

19.0 GB / 24.0 GB

Memory breakdown

Weights12.2 GB

KV Cache3.2 GB

Runtime1.2 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsGranite Code 20B on Tesla P40 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: 18.1 tok/s decode · 10.7s TTFT (warm) · 45 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	18.1 tok/s	5843 ms	8K
Coding	A	Runs well	18.1 tok/s	10713 ms	8K
Agentic Coding	A	Tight fit	18.1 tok/s	15583 ms	8K
Reasoning	A	Runs well	18.1 tok/s	12661 ms	8K
RAG	A	Tight fit	18.1 tok/s	19478 ms	8K

Quantization options

How Granite Code 20B (20B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.8 GB	Low	A77
Q3_K_S	3	9.8 GB	Low	A78
NVFP4	4	11.2 GB	Medium	A79
Q4_K_M	4	12.2 GB	Medium	A80
Q5_K_M	5	14.4 GB	High	A80
Q6_KBest for your GPU	6	16.4 GB	High	A79
Q8_0	8	21.4 GB	Very High	F0
F16	16	41.0 GB	Maximum	F0

Get started

Copy-paste commands to run Granite Code 20B on your machine.

Run

ollama run granite-code:20b

Your hardware

More models your Tesla P40 24GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	30.9 tok/s
Qwen 3.5 27B	27B	S	13.4 tok/s
Qwen 3.6 27B	27B	S	13.4 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	31.9 tok/s
Qwen 3.5 35B A3B	35B	A	16.7 tok/s

Frequently asked questions

Can Tesla P40 24GB run Granite Code 20B?

Yes, Tesla P40 24GB can run Granite Code 20B with a A grade (Runs well). Expected decode speed: 18.1 tok/s.

How much VRAM does Granite Code 20B need?

Granite Code 20B (20B parameters) requires approximately 19.0 GB of memory with Q4_K_M quantization.

What is the best quantization for Granite Code 20B?

The recommended quantization for Granite Code 20B is Q4_K_M, which balances quality and memory efficiency.

What speed will Granite Code 20B run at on Tesla P40 24GB?

On Tesla P40 24GB, Granite Code 20B achieves approximately 18.1 tokens per second decode speed with a time-to-first-token of 10713ms using Q4_K_M quantization.

Can Tesla P40 24GB run Granite Code 20B for coding?

For coding workloads, Granite Code 20B on Tesla P40 24GB receives a A grade with 18.1 tok/s and 8K context.

What context window can Granite Code 20B use on Tesla P40 24GB?

On Tesla P40 24GB, Granite Code 20B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.

See all results for Tesla P40 24GB See all hardware for Granite Code 20B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/granite-code-20b-on-tesla-p40-24gb" 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

18.1 tok/s

5843 ms

Coding

Runs well

18.1 tok/s

10713 ms

Agentic Coding

Tight fit

18.1 tok/s

15583 ms

Reasoning

Runs well

18.1 tok/s

12661 ms

RAG

Tight fit

18.1 tok/s

19478 ms

Quantization options

How Granite Code 20B (20B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.8 GB	Low	A77
Q3_K_S	3	9.8 GB	Low	A78
NVFP4	4	11.2 GB	Medium	A79
Q4_K_M	4	12.2 GB	Medium	A80
Q5_K_M	5	14.4 GB	High	A80
Q6_KBest for your GPU	6	16.4 GB	High	A79
Q8_0	8	21.4 GB	Very High	F0
F16	16	41.0 GB	Maximum	F0

Model

Params

Grade

Decode

Capabilities

Qwen3-Coder 30B A3B Instruct

30.5B

30.9 tok/s

Qwen 3.5 27B

27B

13.4 tok/s

Qwen 3.6 27B

27B

13.4 tok/s

Qwen3-VL 30B A3B Instruct

30B

31.9 tok/s

Qwen 3.5 35B A3B

35B

16.7 tok/s

Frequently asked questions

Can Tesla P40 24GB run Granite Code 20B?

Yes, Tesla P40 24GB can run Granite Code 20B with a A grade (Runs well). Expected decode speed: 18.1 tok/s.

How much VRAM does Granite Code 20B need?

Granite Code 20B (20B parameters) requires approximately 19.0 GB of memory with Q4_K_M quantization.

What is the best quantization for Granite Code 20B?

The recommended quantization for Granite Code 20B is Q4_K_M, which balances quality and memory efficiency.

What speed will Granite Code 20B run at on Tesla P40 24GB?

On Tesla P40 24GB, Granite Code 20B achieves approximately 18.1 tokens per second decode speed with a time-to-first-token of 10713ms using Q4_K_M quantization.

Can Tesla P40 24GB run Granite Code 20B for coding?

For coding workloads, Granite Code 20B on Tesla P40 24GB receives a A grade with 18.1 tok/s and 8K context.

What context window can Granite Code 20B use on Tesla P40 24GB?

On Tesla P40 24GB, Granite Code 20B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.