Can Qwen 3.5 122B A10B run on NVIDIA GH200 96GB?

YES — Tight Fit

S96Excellent

Estimated from fit model

Qwen 3.5 122B A10B needs ~87.4 GB VRAM. NVIDIA GH200 96GB has 96.0 GB. With Q4_K_M quantization, expect ~130 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: 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) — 87.4 GB, 130.3 tok/s, Tight fit

87.4 GB required96.0 GB available

91% VRAM used

Fit status

Tight fit

Decode

130.3 tok/s

TTFT

1486 ms

Safe context

73K

Memory

87.4 GB / 96.0 GB

Memory breakdown

Weights74.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsQwen 3.5 122B A10B on NVIDIA GH200 96GB
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: 130.3 tok/s decode · 1.5s TTFT (warm) · 326 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Tight fit	130.3 tok/s	811 ms	73K
Coding	S	Tight fit	130.3 tok/s	1486 ms	73K
Agentic Coding	S	Tight fit	119.1 tok/s	2365 ms	73K
Reasoning	S	Tight fit	130.3 tok/s	1757 ms	73K
RAG	S	Tight fit	130.3 tok/s	2702 ms	73K

Quantization options

How Qwen 3.5 122B A10B (122B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	47.6 GB	Low	S90
Q3_K_S	3	59.8 GB	Low	S90
NVFP4	4

Get started

Copy-paste commands to run Qwen 3.5 122B A10B on your machine.

Run

lms load Qwen3.5-122B-A10B-Instruct && lms server start

Your hardware

More models your NVIDIA GH200 96GB can run

Model	Params	Grade	Decode	Capabilities
Devstral 2 123B Instruct	123B	S	47 tok/s

Frequently asked questions

Can NVIDIA GH200 96GB run Qwen 3.5 122B A10B?

Yes, NVIDIA GH200 96GB can run Qwen 3.5 122B A10B with a S grade (Tight fit). Expected decode speed: 130.3 tok/s.

How much VRAM does Qwen 3.5 122B A10B need?

Qwen 3.5 122B A10B (122B parameters) requires approximately 87.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 3.5 122B A10B?

The recommended quantization for Qwen 3.5 122B A10B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 3.5 122B A10B run at on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Qwen 3.5 122B A10B achieves approximately 130.3 tokens per second decode speed with a time-to-first-token of 1486ms using Q4_K_M quantization.

Can NVIDIA GH200 96GB run Qwen 3.5 122B A10B for coding?

For coding workloads, Qwen 3.5 122B A10B on NVIDIA GH200 96GB receives a S grade with 130.3 tok/s and 73K context.

What context window can Qwen 3.5 122B A10B use on NVIDIA GH200 96GB?

On NVIDIA GH200 96GB, Qwen 3.5 122B A10B can safely use up to 73K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for NVIDIA GH200 96GB See all hardware for Qwen 3.5 122B A10B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-3.5-122b-a10b-on-gh200-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: