Can Codestral 21B Pruned i1 run on NVIDIA H200 141GB?

YES — Runs Great

C46Usable

Estimated from fit model

Codestral 21B Pruned i1 needs ~30.6 GB VRAM. NVIDIA H200 141GB has 141.0 GB. With Q4_K_M quantization, expect ~294 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) — 30.6 GB, 294.0 tok/s, Runs well

30.6 GB required141.0 GB available

22% VRAM used

Fit status

Runs well

Decode

294.0 tok/s

TTFT

659 ms

Safe context

734K

Memory

30.6 GB / 141.0 GB

Memory breakdown

Weights12.8 GB

KV Cache2.5 GB

Runtime1.2 GB

Headroom14.1 GB

See how fast it feels

See how fast it feelsCodestral 21B Pruned i1 on NVIDIA H200 141GB
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: 294.0 tok/s decode · 659ms TTFT (warm) · 735 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	294.0 tok/s	359 ms	734K
Coding	C	Runs well	294.0 tok/s	659 ms	734K
Agentic Coding	C	Runs well	294.0 tok/s	958 ms	734K
Reasoning	C	Runs well	294.0 tok/s	778 ms	734K
RAG	C	Runs well	294.0 tok/s	1197 ms	734K

Inference speed

Codestral 21B Pruned i1 inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Codestral 21B Pruned i1 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~94 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	93.7	Fits
RTX 4090 24GB	24 GB	Q4_K_M	59.8	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	54.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	51.1	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	43.5	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	36.2	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	35.2	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	35.2	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	34.3	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	27.7	Heavy offload
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	22.2	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	18.7	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	17.2	Fits
RTX 4070 12GB	12 GB	Q4_K_M	9.8	Too big
RTX 3060 12GB	12 GB	Q4_K_M	6.2	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.3	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Codestral 21B Pruned i1 (21B params) fits at each quantization level on NVIDIA H200 141GB (141.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	D37
Q3_K_S	3	10.3 GB	Low	D38
NVFP4	4	11.8 GB	Medium	D38
Q4_K_M	4	12.8 GB	Medium	D38
Q5_K_M	5	15.1 GB	High	D38
Q6_K	6	17.2 GB	High	D38
Q8_0	8	22.5 GB	Very High	D38
F16Best for your GPU	16	43.1 GB	Maximum	C41

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 H200 141GB run Codestral 21B Pruned i1?

Yes, NVIDIA H200 141GB can run Codestral 21B Pruned i1 with a C grade (Runs well). Expected decode speed: 294.0 tok/s.

How much VRAM does Codestral 21B Pruned i1 need?

Codestral 21B Pruned i1 (21B parameters) requires approximately 30.6 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 H200 141GB?

On NVIDIA H200 141GB, Codestral 21B Pruned i1 achieves approximately 294.0 tokens per second decode speed with a time-to-first-token of 659ms using Q4_K_M quantization.

Can NVIDIA H200 141GB run Codestral 21B Pruned i1 for coding?

For coding workloads, Codestral 21B Pruned i1 on NVIDIA H200 141GB receives a C grade with 294.0 tok/s and 734K context.

What context window can Codestral 21B Pruned i1 use on NVIDIA H200 141GB?

On NVIDIA H200 141GB, Codestral 21B Pruned i1 can safely use up to 734K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for NVIDIA H200 141GB 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-h200-141gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: