Can Codestral 2 25.08 run on RTX 5000 Ada 32GB?

YES — Runs Great

S86Excellent

Estimated from fit model

Codestral 2 25.08 needs ~20.0 GB VRAM. RTX 5000 Ada 32GB has 32.0 GB. With Q4_K_M quantization, expect ~33 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: MediumStack: 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) — 20.0 GB, 33.0 tok/s, Runs well

20.0 GB required32.0 GB available

63% VRAM used

Fit status

Runs well

Decode

33.0 tok/s

TTFT

5873 ms

Safe context

95K

Memory

20.0 GB / 32.0 GB

Memory breakdown

Weights13.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom3.2 GB

See how fast it feels

See how fast it feelsCodestral 2 25.08 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: 33.0 tok/s decode · 5.9s TTFT (warm) · 82 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	S	Runs well	33.0 tok/s	3204 ms	95K
Coding	S	Runs well	33.0 tok/s	5873 ms	95K
Agentic Coding	S	Runs well	33.0 tok/s	8543 ms	95K
Reasoning	S	Runs well	33.0 tok/s	6941 ms	95K
RAG	S	Runs well	33.0 tok/s	10679 ms	95K

Quantization options

How Codestral 2 25.08 (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	A80
Q3_K_S	3	10.8 GB	Low	A81
NVFP4	4	12.3 GB	Medium	A81
Q4_K_M	4	13.4 GB	Medium	A82
Q5_K_M	5	15.8 GB	High	A83
Q6_K	6	18.0 GB	High	A84
Q8_0Best for your GPU	8	23.5 GB	Very High	A83
F16	16	45.1 GB	Maximum	F0

Get started

Copy-paste commands to run Codestral 2 25.08 on your machine.

Run

lms load codestral-2508 && lms server start

Your hardware

More models your RTX 5000 Ada 32GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	69.7 tok/s
Qwen 3.5 27B	27B	S	30.2 tok/s
Qwen 3.6 27B	27B	S	23 tok/s
Qwen 3.6 35B A3B	35B	S	58.6 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	72.1 tok/s

Frequently asked questions

Can RTX 5000 Ada 32GB run Codestral 2 25.08?

Yes, RTX 5000 Ada 32GB can run Codestral 2 25.08 with a S grade (Runs well). Expected decode speed: 33.0 tok/s.

How much VRAM does Codestral 2 25.08 need?

Codestral 2 25.08 (22B parameters) requires approximately 20.0 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 2 25.08?

The recommended quantization for Codestral 2 25.08 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 2 25.08 run at on RTX 5000 Ada 32GB?

On RTX 5000 Ada 32GB, Codestral 2 25.08 achieves approximately 33.0 tokens per second decode speed with a time-to-first-token of 5873ms using Q4_K_M quantization.

Can RTX 5000 Ada 32GB run Codestral 2 25.08 for coding?

For coding workloads, Codestral 2 25.08 on RTX 5000 Ada 32GB receives a S grade with 33.0 tok/s and 95K context.

What context window can Codestral 2 25.08 use on RTX 5000 Ada 32GB?

On RTX 5000 Ada 32GB, Codestral 2 25.08 can safely use up to 95K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

See all results for RTX 5000 Ada 32GB See all hardware for Codestral 2 25.08

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/codestral-2-25.08-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: