Can Devstral 2 123B Instruct run on NVIDIA GH200 96GB?

YES — Tight Fit

S95Excellent

○Estimated from fit model

Devstral 2 123B Instruct needs ~90.9 GB VRAM. NVIDIA GH200 96GB has 96.0 GB. With Q4_K_M quantization, expect ~43 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: 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) — 90.9 GB, 47.0 tok/s, Tight fit

90.9 GB required96.0 GB available

95% VRAM used

Fit status

Tight fit

Decode

47.0 tok/s

TTFT

4123 ms

Safe context

31K

Memory

90.9 GB / 96.0 GB

Memory breakdown

Weights75.0 GB

KV Cache5.4 GB

Runtime0.9 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsDevstral 2 123B Instruct 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: 47.0 tok/s decode · 4.1s TTFT (warm) · 117 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Tight fit	43.2 tok/s	2445 ms	31K
Coding	S	Tight fit	43.2 tok/s	4483 ms	31K
Agentic Coding	S	Runs with offload	36.7 tok/s	7681 ms	31K
Reasoning	S	Tight fit	43.2 tok/s	5298 ms	31K
RAG	S	Runs with offload	36.7 tok/s	9602 ms	31K

Quantization options

How Devstral 2 123B Instruct (123B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	48.0 GB	Low	S91
Q3_K_S	3	60.3 GB	Low	S91
NVFP4	4

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

See all results for NVIDIA GH200 96GB See all hardware for Devstral 2 123B Instruct

URL: https://willitrunai.com/can-run/devstral-2-123b-on-gh200-96gb

⇱