Can Codestral 2 25.08 run on NVIDIA GH200 96GB?

YES — Runs Great

A82Great

Estimated from fit model

Codestral 2 25.08 needs ~26.4 GB VRAM. NVIDIA GH200 96GB has 96.0 GB. With Q4_K_M quantization, expect ~232 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) — 26.4 GB, 231.8 tok/s, Runs well

26.4 GB required96.0 GB available

27% VRAM used

Fit status

Runs well

Decode

231.8 tok/s

TTFT

835 ms

Safe context

256K

Memory

26.4 GB / 96.0 GB

Memory breakdown

Weights13.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsCodestral 2 25.08 on NVIDIA GH200 96GB
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: 231.8 tok/s decode · 835ms TTFT (warm) · 579 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	231.8 tok/s	456 ms	256K
Coding	A	Runs well	231.8 tok/s	835 ms	256K
Agentic Coding	A	Runs well	231.8 tok/s	1215 ms	256K
Reasoning	A	Runs well	231.8 tok/s	987 ms	256K
RAG	A	Runs well	231.8 tok/s	1519 ms	256K

Quantization options

How Codestral 2 25.08 (22B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	A74
Q3_K_S	3	10.8 GB	Low	A74
NVFP4	4	12.3 GB	Medium	A74
Q4_K_M	4	13.4 GB	Medium	A74
Q5_K_M	5	15.8 GB	High	A74
Q6_K	6	18.0 GB	High	A75
Q8_0	8	23.5 GB	Very High	A75
F16Best for your GPU	16	45.1 GB	Maximum	A80

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 GH200 96GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	47 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	489.9 tok/s
Qwen 3.5 27B	27B	S	212.5 tok/s
Qwen 3.6 27B	27B	S	132.4 tok/s
Qwen 3.5 122B A10B	122B	S	130.3 tok/s

Frequently asked questions

Can NVIDIA GH200 96GB run Codestral 2 25.08?

Yes, NVIDIA GH200 96GB can run Codestral 2 25.08 with a A grade (Runs well). Expected decode speed: 231.8 tok/s.

How much VRAM does Codestral 2 25.08 need?

Codestral 2 25.08 (22B parameters) requires approximately 26.4 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 NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Codestral 2 25.08 achieves approximately 231.8 tokens per second decode speed with a time-to-first-token of 835ms using Q4_K_M quantization.

Can NVIDIA GH200 96GB run Codestral 2 25.08 for coding?

For coding workloads, Codestral 2 25.08 on NVIDIA GH200 96GB receives a A grade with 231.8 tok/s and 256K context.

What context window can Codestral 2 25.08 use on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Codestral 2 25.08 can safely use up to 256K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

See all results for NVIDIA GH200 96GB 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-gh200-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: