Can Codestral 2 25.08 run on NVIDIA H200 PCIe 141GB?

YES — Runs Great

A81Great

Estimated from fit model

Codestral 2 25.08 needs ~30.9 GB VRAM. NVIDIA H200 PCIe 141GB has 141.0 GB. With Q4_K_M quantization, expect ~288 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) — 30.9 GB, 288.4 tok/s, Runs well

30.9 GB required141.0 GB available

22% VRAM used

Fit status

Runs well

Decode

288.4 tok/s

TTFT

671 ms

Safe context

256K

Memory

30.9 GB / 141.0 GB

Memory breakdown

Weights13.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom14.1 GB

See how fast it feels

See how fast it feelsCodestral 2 25.08 on NVIDIA H200 PCIe 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: 288.4 tok/s decode · 671ms TTFT (warm) · 721 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	288.4 tok/s	366 ms	256K
Coding	A	Runs well	288.4 tok/s	671 ms	256K
Agentic Coding	A	Runs well	288.4 tok/s	976 ms	256K
Reasoning	A	Runs well	288.4 tok/s	793 ms	256K
RAG	A	Runs well	288.4 tok/s	1220 ms	256K

Inference speed

Codestral 2 25.08 inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Codestral 2 25.08 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~96 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	96.2	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	52.0	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	41.9	Fits
RTX 4090 24GB	24 GB	Q4_K_M	41.7	Fits
RTX 3090 24GB	24 GB	Q4_K_M	38.2	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 M2 Ultra 128GB	128 GB	Q4_K_M	34.9	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	33.1	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	22.2	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	18.6	Heavy offload
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	18.1	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	16.6	Fits
RTX 4070 12GB	12 GB	Q4_K_M	6.6	Too big
RTX 3060 12GB	12 GB	Q4_K_M	4.4	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	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 2 25.08 (22B params) fits at each quantization level on NVIDIA H200 PCIe 141GB (141.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	A72
Q3_K_S	3	10.8 GB	Low	A72
NVFP4	4	12.3 GB	Medium	A72
Q4_K_M	4	13.4 GB	Medium	A72
Q5_K_M	5	15.8 GB	High	A73
Q6_K	6	18.0 GB	High	A73
Q8_0	8	23.5 GB	Very High	A73
F16Best for your GPU	16	45.1 GB	Maximum	A76

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 H200 PCIe 141GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	58.4 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	609.7 tok/s
Qwen 3.5 27B	27B	S	264.4 tok/s
Qwen 3.6 27B	27B	S	164.8 tok/s
Qwen 3.5 122B A10B	122B	S	162.1 tok/s

Frequently asked questions

Can NVIDIA H200 PCIe 141GB run Codestral 2 25.08?

Yes, NVIDIA H200 PCIe 141GB can run Codestral 2 25.08 with a A grade (Runs well). Expected decode speed: 288.4 tok/s.

How much VRAM does Codestral 2 25.08 need?

Codestral 2 25.08 (22B parameters) requires approximately 30.9 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 H200 PCIe 141GB?

On NVIDIA H200 PCIe 141GB, Codestral 2 25.08 achieves approximately 288.4 tokens per second decode speed with a time-to-first-token of 671ms using Q4_K_M quantization.

Can NVIDIA H200 PCIe 141GB run Codestral 2 25.08 for coding?

For coding workloads, Codestral 2 25.08 on NVIDIA H200 PCIe 141GB receives a A grade with 288.4 tok/s and 256K context.

What context window can Codestral 2 25.08 use on NVIDIA H200 PCIe 141GB?

On NVIDIA H200 PCIe 141GB, 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 H200 PCIe 141GB 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-h200-pcie-141gb" 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

288.4 tok/s

366 ms

256K

Coding

Runs well

288.4 tok/s

671 ms

256K

Agentic Coding

Runs well

288.4 tok/s

976 ms

256K

Reasoning

Runs well

288.4 tok/s

793 ms

256K

RAG

Runs well

288.4 tok/s

1220 ms

256K

Codestral 2 25.08 inference speed — tokens per second by GPU & Mac

GPU / Mac

Memory

Quant

Speed (tok/s)

Fits?

RTX 5090 32GB

32 GB

Q4_K_M

96.2

Fits

RX 7900 XTX 24GB

24 GB

Q4_K_M

52.0

Fits

Mac Studio M3 Ultra 256GB

256 GB

Q4_K_M

41.9

Fits

RTX 4090 24GB

24 GB

Q4_K_M

41.7

Fits

RTX 3090 24GB

24 GB

Q4_K_M

38.2

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 M2 Ultra 128GB

128 GB

Q4_K_M

34.9

Fits

Mac Studio M1 Ultra 128GB

128 GB

Q4_K_M

33.1

Fits

MacBook Pro M4 Pro 48GB

48 GB

Q4_K_M

22.2

Fits

RTX 4080 Super 16GB

16 GB

Q4_K_M

18.6

Heavy offload

MacBook Pro M3 Max 64GB

64 GB

Q4_K_M

18.1

Fits

MacBook Pro M1 Max 64GB

64 GB

Q4_K_M

16.6

Fits

RTX 4070 12GB

12 GB

Q4_K_M

6.6

Too big

RTX 3060 12GB

12 GB

Q4_K_M

4.4

Too big

RTX 4060 8GB

8 GB

Q4_K_M

2.0

Too big

Quantization options

How Codestral 2 25.08 (22B params) fits at each quantization level on NVIDIA H200 PCIe 141GB (141.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	A72
Q3_K_S	3	10.8 GB	Low	A72
NVFP4	4	12.3 GB	Medium	A72
Q4_K_M	4	13.4 GB	Medium	A72
Q5_K_M	5	15.8 GB	High	A73
Q6_K	6	18.0 GB	High	A73
Q8_0	8	23.5 GB	Very High	A73
F16Best for your GPU	16	45.1 GB	Maximum	A76

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

58.4 tok/s

Qwen3-Coder 30B A3B Instruct

30.5B

609.7 tok/s

Qwen 3.5 27B

27B

264.4 tok/s

Qwen 3.6 27B

27B

164.8 tok/s

Qwen 3.5 122B A10B

122B

162.1 tok/s

Frequently asked questions

Can NVIDIA H200 PCIe 141GB run Codestral 2 25.08?

Yes, NVIDIA H200 PCIe 141GB can run Codestral 2 25.08 with a A grade (Runs well). Expected decode speed: 288.4 tok/s.

How much VRAM does Codestral 2 25.08 need?

Codestral 2 25.08 (22B parameters) requires approximately 30.9 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 H200 PCIe 141GB?

On NVIDIA H200 PCIe 141GB, Codestral 2 25.08 achieves approximately 288.4 tokens per second decode speed with a time-to-first-token of 671ms using Q4_K_M quantization.

Can NVIDIA H200 PCIe 141GB run Codestral 2 25.08 for coding?

For coding workloads, Codestral 2 25.08 on NVIDIA H200 PCIe 141GB receives a A grade with 288.4 tok/s and 256K context.

What context window can Codestral 2 25.08 use on NVIDIA H200 PCIe 141GB?

On NVIDIA H200 PCIe 141GB, 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.