Can Codestral 22B run on RTX 5000 Ada 32GB?

YES — Runs Great

B63Good

Estimated from fit model

Codestral 22B needs ~20.3 GB VRAM. RTX 5000 Ada 32GB has 32.0 GB. With Q4_K_M quantization, expect ~37 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: MediumStack: 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) — 20.3 GB, 36.9 tok/s, Runs well

20.3 GB required32.0 GB available

63% VRAM used

Fit status

Runs well

Decode

36.9 tok/s

TTFT

5245 ms

Safe context

33K

Memory

20.3 GB / 32.0 GB

Memory breakdown

Weights13.4 GB

KV Cache2.4 GB

Runtime1.2 GB

Headroom3.2 GB

See how fast it feels

See how fast it feelsCodestral 22B on RTX 5000 Ada 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: 36.9 tok/s decode · 5.2s TTFT (warm) · 92 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	B	Runs well	36.9 tok/s	2861 ms	33K
Coding	B	Runs well	36.9 tok/s	5245 ms	33K
Agentic Coding	B	Runs well	36.9 tok/s	7629 ms	33K
Reasoning	B	Runs well	36.9 tok/s	6199 ms	33K
RAG	B	Runs well	36.9 tok/s	9536 ms	33K

Quantization options

How Codestral 22B (22B params) fits at each quantization level on RTX 5000 Ada 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	B55
Q3_K_S	3	10.8 GB	Low	B56
NVFP4	4	12.3 GB	Medium	B57
Q4_K_M	4	13.4 GB	Medium	B58
Q5_K_M	5	15.8 GB	High	B59
Q6_K	6	18.0 GB	High	B59
Q8_0Best for your GPU	8	23.5 GB	Very High	B59
F16	16	45.1 GB	Maximum	F0

Get started

Copy-paste commands to run Codestral 22B on your machine.

Run

ollama run codestral

Upgrade options

Hardware that runs Codestral 22B well

MacBook Pro M4 Max 48GBBest value

48 GB Unified (+16)

This setup is broadly balanced for this model.37.4 tok/s decode

~$2,499 MSRP

NVIDIA A100 40GBBudget pick

40 GB VRAM (+8)1555 GB/s (+979)

Raises estimated decode speed by about 183%.104.6 tok/s decode

Raises estimated decode speed by about 183%.

Adds memory headroom for longer context windows and future model growth.

~$10,000 MSRP

Frequently asked questions

Can RTX 5000 Ada 32GB run Codestral 22B?

Yes, RTX 5000 Ada 32GB can run Codestral 22B with a B grade (Runs well). Expected decode speed: 36.9 tok/s.

How much VRAM does Codestral 22B need?

Codestral 22B (22B parameters) requires approximately 20.3 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 22B?

The recommended quantization for Codestral 22B is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 22B run at on RTX 5000 Ada 32GB?

On RTX 5000 Ada 32GB, Codestral 22B achieves approximately 36.9 tokens per second decode speed with a time-to-first-token of 5245ms using Q4_K_M quantization.

Can RTX 5000 Ada 32GB run Codestral 22B for coding?

For coding workloads, Codestral 22B on RTX 5000 Ada 32GB receives a B grade with 36.9 tok/s and 33K context.

What context window can Codestral 22B use on RTX 5000 Ada 32GB?

On RTX 5000 Ada 32GB, Codestral 22B can safely use up to 33K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.

See all results for RTX 5000 Ada 32GB See all hardware for Codestral 22B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/codestral-22b-on-rtx-5000-ada-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

36.9 tok/s

2861 ms

33K

Coding

Runs well

36.9 tok/s

5245 ms

33K

Agentic Coding

Runs well

36.9 tok/s

7629 ms

33K

Reasoning

Runs well

36.9 tok/s

6199 ms

33K

RAG

Runs well

36.9 tok/s

9536 ms

33K

Quantization options

How Codestral 22B (22B params) fits at each quantization level on RTX 5000 Ada 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	B55
Q3_K_S	3	10.8 GB	Low	B56
NVFP4	4	12.3 GB	Medium	B57
Q4_K_M	4	13.4 GB	Medium	B58
Q5_K_M	5	15.8 GB	High	B59
Q6_K	6	18.0 GB	High	B59
Q8_0Best for your GPU	8	23.5 GB	Very High	B59
F16	16	45.1 GB	Maximum	F0

Frequently asked questions

Can RTX 5000 Ada 32GB run Codestral 22B?

Yes, RTX 5000 Ada 32GB can run Codestral 22B with a B grade (Runs well). Expected decode speed: 36.9 tok/s.

How much VRAM does Codestral 22B need?

Codestral 22B (22B parameters) requires approximately 20.3 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 22B?

The recommended quantization for Codestral 22B is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 22B run at on RTX 5000 Ada 32GB?

On RTX 5000 Ada 32GB, Codestral 22B achieves approximately 36.9 tokens per second decode speed with a time-to-first-token of 5245ms using Q4_K_M quantization.

Can RTX 5000 Ada 32GB run Codestral 22B for coding?

For coding workloads, Codestral 22B on RTX 5000 Ada 32GB receives a B grade with 36.9 tok/s and 33K context.

What context window can Codestral 22B use on RTX 5000 Ada 32GB?

On RTX 5000 Ada 32GB, Codestral 22B can safely use up to 33K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.