Can Codestral 21B Pruned i1 run on NVIDIA GH200 96GB?

YES — Runs Great

C47Usable

Estimated from fit model

Codestral 21B Pruned i1 needs ~26.1 GB VRAM. NVIDIA GH200 96GB has 96.0 GB. With Q4_K_M quantization, expect ~253 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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) — 26.1 GB, 252.9 tok/s, Runs well

26.1 GB required96.0 GB available

27% VRAM used

Fit status

Runs well

Decode

252.9 tok/s

TTFT

765 ms

Safe context

471K

Memory

26.1 GB / 96.0 GB

Memory breakdown

Weights12.8 GB

KV Cache2.5 GB

Runtime1.2 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsCodestral 21B Pruned i1 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: 252.9 tok/s decode · 765ms TTFT (warm) · 632 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	C	Runs well	252.9 tok/s	418 ms	471K
Coding	C	Runs well	252.9 tok/s	765 ms	471K
Agentic Coding	C	Runs well	252.9 tok/s	1113 ms	471K
Reasoning	C	Runs well	252.9 tok/s	905 ms	471K
RAG	C	Runs well	252.9 tok/s	1392 ms	471K

Quantization options

How Codestral 21B Pruned i1 (21B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	D39
Q3_K_S	3	10.3 GB	Low	D39
NVFP4	4	11.8 GB	Medium	D39
Q4_K_M	4	12.8 GB	Medium	D39
Q5_K_M	5	15.1 GB	High	D39
Q6_K	6	17.2 GB	High	D40
Q8_0	8	22.5 GB	Very High	C40
F16Best for your GPU	16	43.1 GB	Maximum	C45

Get started

Copy-paste commands to run Codestral 21B Pruned i1 on your machine.

Run

lms load hf-mradermacher--codestral-21b-pruned-i1-gguf && lms server start

Frequently asked questions

Can NVIDIA GH200 96GB run Codestral 21B Pruned i1?

Yes, NVIDIA GH200 96GB can run Codestral 21B Pruned i1 with a C grade (Runs well). Expected decode speed: 252.9 tok/s.

How much VRAM does Codestral 21B Pruned i1 need?

Codestral 21B Pruned i1 (21B parameters) requires approximately 26.1 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 21B Pruned i1?

The recommended quantization for Codestral 21B Pruned i1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 21B Pruned i1 run at on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Codestral 21B Pruned i1 achieves approximately 252.9 tokens per second decode speed with a time-to-first-token of 765ms using Q4_K_M quantization.

Can NVIDIA GH200 96GB run Codestral 21B Pruned i1 for coding?

For coding workloads, Codestral 21B Pruned i1 on NVIDIA GH200 96GB receives a C grade with 252.9 tok/s and 471K context.

What context window can Codestral 21B Pruned i1 use on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Codestral 21B Pruned i1 can safely use up to 471K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for NVIDIA GH200 96GB See all hardware for Codestral 21B Pruned i1

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-mradermacher--codestral-21b-pruned-i1-gguf-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:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

252.9 tok/s

418 ms

471K

Coding

Runs well

252.9 tok/s

765 ms

471K

Agentic Coding

Runs well

252.9 tok/s

1113 ms

471K

Reasoning

Runs well

252.9 tok/s

905 ms

471K

RAG

Runs well

252.9 tok/s

1392 ms

471K

Quantization options

How Codestral 21B Pruned i1 (21B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	D39
Q3_K_S	3	10.3 GB	Low	D39
NVFP4	4	11.8 GB	Medium	D39
Q4_K_M	4	12.8 GB	Medium	D39
Q5_K_M	5	15.1 GB	High	D39
Q6_K	6	17.2 GB	High	D40
Q8_0	8	22.5 GB	Very High	C40
F16Best for your GPU	16	43.1 GB	Maximum	C45

Frequently asked questions

Can NVIDIA GH200 96GB run Codestral 21B Pruned i1?

Yes, NVIDIA GH200 96GB can run Codestral 21B Pruned i1 with a C grade (Runs well). Expected decode speed: 252.9 tok/s.

How much VRAM does Codestral 21B Pruned i1 need?

Codestral 21B Pruned i1 (21B parameters) requires approximately 26.1 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 21B Pruned i1?

The recommended quantization for Codestral 21B Pruned i1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 21B Pruned i1 run at on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Codestral 21B Pruned i1 achieves approximately 252.9 tokens per second decode speed with a time-to-first-token of 765ms using Q4_K_M quantization.

Can NVIDIA GH200 96GB run Codestral 21B Pruned i1 for coding?

For coding workloads, Codestral 21B Pruned i1 on NVIDIA GH200 96GB receives a C grade with 252.9 tok/s and 471K context.

What context window can Codestral 21B Pruned i1 use on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Codestral 21B Pruned i1 can safely use up to 471K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.