Can Codestral 2 25.08 run on Tesla P40 24GB?

YES — Runs Great

S85Excellent

○Estimated from fit model

Codestral 2 25.08 needs ~19.2 GB VRAM. Tesla P40 24GB has 24.0 GB. With Q4_K_M quantization, expect ~15 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: 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) — 19.2 GB, 14.6 tok/s, Runs well

19.2 GB required24.0 GB available

80% VRAM used

Fit status

Runs well

Decode

14.6 tok/s

TTFT

13258 ms

Safe context

48K

Memory

19.2 GB / 24.0 GB

Memory breakdown

Weights13.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsCodestral 2 25.08 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: 14.6 tok/s decode · 13.3s TTFT (warm) · 37 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	S	Runs well	14.6 tok/s	7232 ms	48K
Coding	S	Runs well	14.6 tok/s	13258 ms	48K
Agentic Coding	A	Tight fit	14.6 tok/s	19284 ms	48K
Reasoning	S	Runs well	14.6 tok/s	15668 ms	48K
RAG	A	Tight fit	14.6 tok/s	24105 ms	48K

Quantization options

How Codestral 2 25.08 (22B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	A82
Q3_K_S	3	10.8 GB	Low	A84
NVFP4	4	12.3 GB	Medium	A85
Q4_K_M	4	13.4 GB	Medium	A84
Q5_K_M	5	15.8 GB	High	A84
Q6_KBest for your GPU	6	18.0 GB	High	A84
Q8_0	8	23.5 GB	Very High	F0
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 Tesla P40 24GB can run

Model	Params	Grade	Decode
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	30.9 tok/s
👁 Alibaba Qwen 3.5 27B	27B	S	13.4 tok/s
👁 Alibaba Qwen 3.6 27B	27B	S	10.2 tok/s
👁 Alibaba Qwen 3.6 35B A3B	35B	A	12.7 tok/s
👁 Alibaba Qwen3-VL 30B A3B Instruct	30B	S	31.9 tok/s

Frequently asked questions

See all results for Tesla P40 24GB See all hardware for Codestral 2 25.08

URL: https://willitrunai.com/can-run/codestral-2-25.08-on-tesla-p40-24gb

⇱ Codestral 2 25.08 on Tesla P40 24GB? YES