Can Devstral 2 123B Instruct run on NVIDIA H200 PCIe 141GB?

YES — Runs Great

S98Excellent

Estimated from fit model

Devstral 2 123B Instruct needs ~95.4 GB VRAM. NVIDIA H200 PCIe 141GB has 141.0 GB. With Q4_K_M quantization, expect ~58 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) — 95.4 GB, 58.4 tok/s, Runs well

95.4 GB required141.0 GB available

68% VRAM used

Fit status

Runs well

Decode

58.4 tok/s

TTFT

3313 ms

Safe context

152K

Memory

95.4 GB / 141.0 GB

Memory breakdown

Weights75.0 GB

KV Cache5.4 GB

Runtime0.9 GB

Headroom14.1 GB

See how fast it feels

See how fast it feelsDevstral 2 123B Instruct 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: 58.4 tok/s decode · 3.3s TTFT (warm) · 146 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	S	Runs well	58.4 tok/s	1807 ms	152K
Coding	S	Runs well	58.4 tok/s	3313 ms	152K
Agentic Coding	S	Runs well	58.4 tok/s	4819 ms	152K
Reasoning	S	Runs well	58.4 tok/s	3915 ms	152K
RAG	S	Runs well	58.4 tok/s	6023 ms	152K

Inference speed

Devstral 2 123B Instruct inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Devstral 2 123B Instruct at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is MacBook Pro M4 Max 128GB at ~8 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?
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	8.2	Offloads
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	8.1	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	6.3	Offloads
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	6.0	Offloads
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	3.9	Too big
2× RX 7900 XTX 24GB	48 GB	Q4_K_M	3.7	Too big
2× RTX 4090 24GB	48 GB	Q4_K_M	2.6	Too big
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	2.5	Too big
2× RTX 3090 24GB	48 GB	Q4_K_M	2.2	Too big
RTX 5090 32GB	32 GB	Q4_K_M	2.0	Too big
RTX 4090 24GB	24 GB	Q4_K_M	2.0	Too big
RTX 4080 Super 16GB	16 GB	Q4_K_M	2.0	Too big
RTX 3090 24GB	24 GB	Q4_K_M	2.0	Too big
RTX 4070 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 3060 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	2.0	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	2.0	Too big
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	2.0	Too big
4× RTX 3060 12GB	48 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 Devstral 2 123B Instruct (123B params) fits at each quantization level on NVIDIA H200 PCIe 141GB (141.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	48.0 GB	Low	S87
Q3_K_S	3	60.3 GB	Low	S89
NVFP4	4	68.9 GB	Medium	S90
Q4_K_M	4	75.0 GB	Medium	S91
Q5_K_M	5	88.6 GB	High	S91
Q6_KBest for your GPU	6	100.9 GB	High	S91
Q8_0	8	131.6 GB	Very High	F0
F16	16	252.2 GB	Maximum	F0

Get started

Copy-paste commands to run Devstral 2 123B Instruct on your machine.

Run

lms load Devstral-2-123B-Instruct-2512 && lms server start

Frequently asked questions

Can NVIDIA H200 PCIe 141GB run Devstral 2 123B Instruct?

Yes, NVIDIA H200 PCIe 141GB can run Devstral 2 123B Instruct with a S grade (Runs well). Expected decode speed: 58.4 tok/s.

How much VRAM does Devstral 2 123B Instruct need?

Devstral 2 123B Instruct (123B parameters) requires approximately 95.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Devstral 2 123B Instruct?

The recommended quantization for Devstral 2 123B Instruct is Q4_K_M, which balances quality and memory efficiency.

What speed will Devstral 2 123B Instruct run at on NVIDIA H200 PCIe 141GB?

On NVIDIA H200 PCIe 141GB, Devstral 2 123B Instruct achieves approximately 58.4 tokens per second decode speed with a time-to-first-token of 3313ms using Q4_K_M quantization.

Can NVIDIA H200 PCIe 141GB run Devstral 2 123B Instruct for coding?

For coding workloads, Devstral 2 123B Instruct on NVIDIA H200 PCIe 141GB receives a S grade with 58.4 tok/s and 152K context.

What context window can Devstral 2 123B Instruct use on NVIDIA H200 PCIe 141GB?

On NVIDIA H200 PCIe 141GB, Devstral 2 123B Instruct can safely use up to 152K 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 Devstral 2 123B Instruct

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/devstral-2-123b-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: