Can Codestral 22B run on RTX 4090 24GB?

YES — Runs Great

B65Good

●Measured on real hardware· rtx-4090-24gb

Codestral 22B needs ~19.2 GB VRAM. RTX 4090 24GB has 24.0 GB. With Q4_K_M quantization, expect ~45 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) — 19.2 GB, 44.3 tok/s, Runs well

19.2 GB required24.0 GB available

80% VRAM used

Fit status

Runs well

Decode

44.3 tok/s

TTFT

4368 ms

Safe context

33K

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 22B on RTX 4090 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: 44.3 tok/s decode · 4.4s TTFT (warm) · 111 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	45.0 tok/s	1947 ms	33K
Coding	B	Runs well	45.0 tok/s	3570 ms	33K
Agentic Coding	B	Tight fit	45.0 tok/s	5193 ms	33K
Reasoning	B	Runs well	45.0 tok/s	4219 ms	33K
RAG	B	Tight fit	45.0 tok/s	6491 ms	33K

Quantization options

How Codestral 22B (22B params) fits at each quantization level on RTX 4090 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	B58
Q3_K_S	3	10.8 GB	Low	B60
NVFP4	4

Get started

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

Run

ollama run codestral

Frequently asked questions

See all results for RTX 4090 24GB See all hardware for Codestral 22B

URL: https://willitrunai.com/can-run/codestral-22b-on-rtx-4090-24gb

⇱