Will It Run AI

Can Devstral 2 123B Instruct run on NVIDIA A100 80GB?

BARELY — Tight on Memory

A81Great
Estimated from fit model

Devstral 2 123B Instruct needs ~89.3 GB VRAM. NVIDIA A100 80GB has 80.0 GB. With Q4_K_M quantization, expect ~16 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: Host offload
Share:

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) — 89.3 GB, 17.7 tok/s, Very compromised (needs ~7.8 GB host RAM)
89.3 GB required80.0 GB available
112% VRAM needed

9.3 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~7.8 GB host RAM)

Decode

17.7 tok/s

TTFT

10963 ms

Safe context

4K

Memory

89.3 GB / 80.0 GB

Offload

10%

Memory breakdown

Weights75.0 GB
KV Cache5.4 GB
Runtime0.9 GB
Headroom8.0 GB

See how fast it feels

See how fast it feelsDevstral 2 123B Instruct on NVIDIA A100 80GB
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: 17.7 tok/s decode · 11.0s TTFT (warm) · 44 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

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

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

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

Increase host RAM if you keep offloading

This setup may need roughly {ram} GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatAVery compromised17.1 tok/s6183 ms4K
CodingAVery compromised16.2 tok/s11922 ms4K
Agentic CodingAVery compromised14.7 tok/s19095 ms4K
ReasoningAVery compromised16.2 tok/s14089 ms4K
RAGAVery compromised14.7 tok/s23869 ms4K

Quantization options

How Devstral 2 123B Instruct (123B params) fits at each quantization level on NVIDIA A100 80GB (80.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
48.0 GB
LowS91
Q3_K_SBest for your GPU
3
60.3 GB
LowS91
NVFP4
4
68.9 GB
MediumF0
Q4_K_M
4
75.0 GB
MediumF0
Q5_K_M
5
88.6 GB
HighF0
Q6_K
6
100.9 GB
HighF0
Q8_0
8
131.6 GB
Very HighF0
F16
16
252.2 GB
MaximumF0

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 A100 80GB run Devstral 2 123B Instruct?

Yes, NVIDIA A100 80GB can run Devstral 2 123B Instruct with a A grade (Very compromised). Expected decode speed: 16.2 tok/s.

How much VRAM does Devstral 2 123B Instruct need?

Devstral 2 123B Instruct (123B parameters) requires approximately 89.3 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 A100 80GB?

On NVIDIA A100 80GB, Devstral 2 123B Instruct achieves approximately 16.2 tokens per second decode speed with a time-to-first-token of 11922ms using Q4_K_M quantization.

Can NVIDIA A100 80GB run Devstral 2 123B Instruct for coding?

For coding workloads, Devstral 2 123B Instruct on NVIDIA A100 80GB receives a A grade with 16.2 tok/s and 4K context.

What context window can Devstral 2 123B Instruct use on NVIDIA A100 80GB?

On NVIDIA A100 80GB, Devstral 2 123B Instruct can safely use up to 4K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

What should I upgrade first if Devstral 2 123B Instruct feels slow on NVIDIA A100 80GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

See all results for NVIDIA A100 80GBSee 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-a100-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: