Can Qwen 3.5 397B A17B run on Gaudi 3 128GB?

NO — Won't Fit

F0Won't run

Estimated from fit model

Qwen 3.5 397B A17B needs ~258.7 GB but Gaudi 3 128GB only has 128.0 GB. Try a smaller quantization or lighter model.

Runtime: llama.cppCapacity: No fitBandwidth: HighStack: StandardBottleneck: Memory capacity

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) — 258.7 GB, exceeds 128.0 GB available

258.7 GB required128.0 GB available

202% VRAM needed

130.7 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

6.4 tok/s

TTFT

30403 ms

Safe context

Memory

258.7 GB / 128.0 GB

Offload

50%

Memory breakdown

Weights242.2 GB

KV Cache2.9 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsQwen 3.5 397B A17B 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: 6.4 tok/s decode · 30.4s TTFT (warm) · 16 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 258.7 GB, but this setup only exposes 128.0 GB of usable VRAM.

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

Add more VRAM headroom

The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.

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	F	Too heavy	6.4 tok/s	16397 ms	4K
Coding	F	Too heavy	6.4 tok/s	30403 ms	4K
Agentic Coding	F	Too heavy	6.2 tok/s	45229 ms	4K
Reasoning	F	Too heavy	6.4 tok/s	35931 ms	4K
RAG	F	Too heavy	6.2 tok/s	56536 ms	4K

Quantization options

How Qwen 3.5 397B A17B (397B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	154.8 GB	Low	F0
Q3_K_S	3	194.5 GB	Low	F0
NVFP4	4	222.3 GB	Medium	F0
Q4_K_M	4	242.2 GB	Medium	F0
Q5_K_M	5	285.8 GB	High	F0
Q6_K	6	325.5 GB	High	F0
Q8_0	8	424.8 GB	Very High	F0
F16	16	813.8 GB	Maximum	F0

アップグレードオプション

Qwen 3.5 397B A17Bを快適に動かすハードウェア

AMD Instinct MI350X 288GBコスパ重視

288 GB VRAM (+160)8000 GB/s (+4300)

Makes the model fit on the accelerator instead of staying completely out of reach.78.9 tok/sデコード

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

〜$8,000 MSRP

AMD Instinct MI325X 256GBコスパ最良

256 GB VRAM (+128)6000 GB/s (+2300)

Makes the model fit on the accelerator instead of staying completely out of reach.39.2 tok/sデコード

Makes the model fit on the accelerator instead of staying completely out of reach.

Raises estimated decode speed by about 513%.

〜$20,000 MSRP

Frequently asked questions

Can Gaudi 3 128GB run Qwen 3.5 397B A17B?

No, Qwen 3.5 397B A17B requires more memory than Gaudi 3 128GB provides.

How much VRAM does Qwen 3.5 397B A17B need?

Qwen 3.5 397B A17B (397B parameters) requires approximately 258.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 3.5 397B A17B?

The recommended quantization for Qwen 3.5 397B A17B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 3.5 397B A17B run at on Gaudi 3 128GB?

On Gaudi 3 128GB, Qwen 3.5 397B A17B achieves approximately 6.4 tokens per second decode speed with a time-to-first-token of 30403ms using Q4_K_M quantization.

Can Gaudi 3 128GB run Qwen 3.5 397B A17B for coding?

For coding workloads, Qwen 3.5 397B A17B on Gaudi 3 128GB receives a F grade with 6.4 tok/s and 4K context.

What context window can Qwen 3.5 397B A17B use on Gaudi 3 128GB?

On Gaudi 3 128GB, Qwen 3.5 397B A17B can safely use up to 4K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

What should I upgrade first if Qwen 3.5 397B A17B feels slow on Gaudi 3 128GB?

Add more VRAM headroom. The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.

Would CUDA be a better path than Gaudi 3 128GB for Qwen 3.5 397B A17B?

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 Qwen 3.5 397B A17B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-3.5-397b-a17b-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: