Can Codestral 2 25.08 run on NVIDIA B200 180GB?

YES — Runs Great

A80Great

○Estimated from fit model

Codestral 2 25.08 needs ~34.8 GB VRAM. NVIDIA B200 180GB has 180.0 GB. With Q4_K_M quantization, expect ~308 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) — 34.8 GB, 308.0 tok/s, Runs well

34.8 GB required180.0 GB available

19% VRAM used

Fit status

Runs well

Decode

308.0 tok/s

TTFT

629 ms

Safe context

256K

Memory

34.8 GB / 180.0 GB

Memory breakdown

Weights13.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom18.0 GB

See how fast it feels

See how fast it feelsCodestral 2 25.08 on NVIDIA B200 180GB
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: 308.0 tok/s decode · 629ms TTFT (warm) · 770 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	A	Runs well	308.0 tok/s	350 ms	256K
Coding	A	Runs well	308.0 tok/s	629 ms	256K
Agentic Coding	A	Runs well	308.0 tok/s	914 ms	256K
Reasoning	A	Runs well	308.0 tok/s	743 ms	256K
RAG	A	Runs well	308.0 tok/s	1143 ms	256K

Quantization options

How Codestral 2 25.08 (22B params) fits at each quantization level on NVIDIA B200 180GB (180.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	A71
Q3_K_S	3	10.8 GB	Low	A71
NVFP4	4

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 NVIDIA B200 180GB can run

Model	Params	Grade	Decode	Capabilities
👁 Mistral Devstral 2 123B Instruct	123B	S	97.4 tok/s
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S

Frequently asked questions

See all results for NVIDIA B200 180GB See all hardware for Codestral 2 25.08

URL: https://willitrunai.com/can-run/codestral-2-25.08-on-b200-180gb

⇱