Can Devstral 2 123B Instruct run on Gaudi 3 128GB?

YES — Runs Great

S97Excellent

Estimated from fit model

Devstral 2 123B Instruct needs ~94.1 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~38 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) — 94.1 GB, 37.5 tok/s, Runs well

94.1 GB required128.0 GB available

74% VRAM used

Fit status

Runs well

Decode

37.5 tok/s

TTFT

5157 ms

Safe context

117K

Memory

94.1 GB / 128.0 GB

Memory breakdown

Weights75.0 GB

KV Cache5.4 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsDevstral 2 123B Instruct on Gaudi 3 128GB
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: 37.5 tok/s decode · 5.2s TTFT (warm) · 94 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs well	37.5 tok/s	2813 ms	117K
Coding	S	Runs well	37.5 tok/s	5157 ms	117K
Agentic Coding	S	Runs well	37.5 tok/s	7501 ms	117K
Reasoning	S	Runs well	37.5 tok/s	6095 ms	117K
RAG	S	Runs well	37.5 tok/s	9377 ms	117K

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 Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	48.0 GB	Low	S88
Q3_K_S	3	60.3 GB	Low	S90
NVFP4	4	68.9 GB	Medium	S91
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 Gaudi 3 128GB run Devstral 2 123B Instruct?

Yes, Gaudi 3 128GB can run Devstral 2 123B Instruct with a S grade (Runs well). Expected decode speed: 37.5 tok/s.

How much VRAM does Devstral 2 123B Instruct need?

Devstral 2 123B Instruct (123B parameters) requires approximately 94.1 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 Gaudi 3 128GB?

On Gaudi 3 128GB, Devstral 2 123B Instruct achieves approximately 37.5 tokens per second decode speed with a time-to-first-token of 5157ms using Q4_K_M quantization.

Can Gaudi 3 128GB run Devstral 2 123B Instruct for coding?

For coding workloads, Devstral 2 123B Instruct on Gaudi 3 128GB receives a S grade with 37.5 tok/s and 117K context.

What context window can Devstral 2 123B Instruct use on Gaudi 3 128GB?

On Gaudi 3 128GB, Devstral 2 123B Instruct can safely use up to 117K 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 Gaudi 3 128GB?

Prefer CUDA if you want the path of least resistance. If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Would CUDA be a better path than Gaudi 3 128GB for Devstral 2 123B Instruct?

Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.

See all results for Gaudi 3 128GB 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-gaudi-3-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: