Can Codestral Mamba 7B run on Gaudi 3 128GB?

YES — Runs Great

A70Great

Estimated from fit model

Codestral Mamba 7B needs ~18.5 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~98 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) — 18.5 GB, 98.0 tok/s, Runs well

18.5 GB required128.0 GB available

14% VRAM used

Fit status

Runs well

Decode

98.0 tok/s

TTFT

1976 ms

Safe context

262K

Memory

18.5 GB / 128.0 GB

Memory breakdown

Weights4.3 GB

KV Cache0.5 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsCodestral Mamba 7B 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: 98.0 tok/s decode · 2.0s TTFT (warm) · 245 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	A	Runs well	98.0 tok/s	1078 ms	262K
Coding	A	Runs well	98.0 tok/s	1976 ms	262K
Agentic Coding	A	Runs well	98.0 tok/s	2873 ms	262K
Reasoning	A	Runs well	98.0 tok/s	2335 ms	262K
RAG	A	Runs well	98.0 tok/s	3592 ms	262K

Quantization options

How Codestral Mamba 7B (7B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.7 GB	Low	B63
Q3_K_S	3	3.4 GB	Low	B63
NVFP4	4	3.9 GB	Medium	B63
Q4_K_M	4	4.3 GB	Medium	B63
Q5_K_M	5	5.0 GB	High	B63
Q6_K	6	5.7 GB	High	B63
Q8_0	8	7.5 GB	Very High	B63
F16Best for your GPU	16	14.3 GB	Maximum	B64

Get started

Copy-paste commands to run Codestral Mamba 7B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "mistralai/Mamba-Codestral-7B-v0.1" \
  --hf-file "Mamba-Codestral-7B-v0.1-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Your hardware

More models your Gaudi 3 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	37.5 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	391.6 tok/s
Qwen 3.5 27B	27B	S	169.8 tok/s
Qwen 3.6 27B	27B	S	105.9 tok/s
Qwen 3.5 122B A10B	122B	S	104.1 tok/s

Frequently asked questions

Can Gaudi 3 128GB run Codestral Mamba 7B?

Yes, Gaudi 3 128GB can run Codestral Mamba 7B with a A grade (Runs well). Expected decode speed: 98.0 tok/s.

How much VRAM does Codestral Mamba 7B need?

Codestral Mamba 7B (7B parameters) requires approximately 18.5 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral Mamba 7B?

The recommended quantization for Codestral Mamba 7B is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral Mamba 7B run at on Gaudi 3 128GB?

On Gaudi 3 128GB, Codestral Mamba 7B achieves approximately 98.0 tokens per second decode speed with a time-to-first-token of 1976ms using Q4_K_M quantization.

Can Gaudi 3 128GB run Codestral Mamba 7B for coding?

For coding workloads, Codestral Mamba 7B on Gaudi 3 128GB receives a A grade with 98.0 tok/s and 262K context.

What context window can Codestral Mamba 7B use on Gaudi 3 128GB?

On Gaudi 3 128GB, Codestral Mamba 7B can safely use up to 262K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

What should I upgrade first if Codestral Mamba 7B 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 Mamba 7B?

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 Mamba 7B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/codestral-mamba-7b-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: