Can Codestral 22B v0.1 run on Gaudi 3 128GB?

YES — Runs Great

C47Usable

Estimated from fit model

Codestral 22B v0.1 needs ~29.7 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~193 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) — 29.7 GB, 193.0 tok/s, Runs well

29.7 GB required128.0 GB available

23% VRAM used

Fit status

Runs well

Decode

193.0 tok/s

TTFT

1003 ms

Safe context

626K

Memory

29.7 GB / 128.0 GB

Memory breakdown

Weights13.4 GB

KV Cache2.6 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsCodestral 22B v0.1 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: 193.0 tok/s decode · 1.0s TTFT (warm) · 483 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	C	Runs well	193.0 tok/s	547 ms	626K
Coding	C	Runs well	193.0 tok/s	1003 ms	626K
Agentic Coding	C	Runs well	193.0 tok/s	1459 ms	626K
Reasoning	C	Runs well	193.0 tok/s	1186 ms	626K
RAG	C	Runs well	193.0 tok/s	1824 ms	626K

Quantization options

How Codestral 22B v0.1 (22B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	D38
Q3_K_S	3	10.8 GB	Low	D38
NVFP4	4	12.3 GB	Medium	D38
Q4_K_M	4	13.4 GB	Medium	D38
Q5_K_M	5	15.8 GB	High	D39
Q6_K	6	18.0 GB	High	D39
Q8_0	8	23.5 GB	Very High	D39
F16Best for your GPU	16	45.1 GB	Maximum	C43

Get started

Copy-paste commands to run Codestral 22B v0.1 on your machine.

Run

lms load hf-lmstudio-community--codestral-22b-v0-1-gguf && lms server start

Frequently asked questions

Can Gaudi 3 128GB run Codestral 22B v0.1?

Yes, Gaudi 3 128GB can run Codestral 22B v0.1 with a C grade (Runs well). Expected decode speed: 193.0 tok/s.

How much VRAM does Codestral 22B v0.1 need?

Codestral 22B v0.1 (22B parameters) requires approximately 29.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 22B v0.1?

The recommended quantization for Codestral 22B v0.1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 22B v0.1 run at on Gaudi 3 128GB?

On Gaudi 3 128GB, Codestral 22B v0.1 achieves approximately 193.0 tokens per second decode speed with a time-to-first-token of 1003ms using Q4_K_M quantization.

Can Gaudi 3 128GB run Codestral 22B v0.1 for coding?

For coding workloads, Codestral 22B v0.1 on Gaudi 3 128GB receives a C grade with 193.0 tok/s and 626K context.

What context window can Codestral 22B v0.1 use on Gaudi 3 128GB?

On Gaudi 3 128GB, Codestral 22B v0.1 can safely use up to 626K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

What should I upgrade first if Codestral 22B v0.1 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 Codestral 22B v0.1?

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 Codestral 22B v0.1

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-lmstudio-community--codestral-22b-v0-1-gguf-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: