Can Qwen 3.5 122B A10B run on AMD Instinct MI350X 288GB?

YES — Runs Great

S92Excellent

Estimated from fit model

Qwen 3.5 122B A10B needs ~106.6 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~235 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) — 106.6 GB, 234.8 tok/s, Runs well

106.6 GB required288.0 GB available

37% VRAM used

Fit status

Runs well

Decode

234.8 tok/s

TTFT

825 ms

Safe context

131K

Memory

106.6 GB / 288.0 GB

Memory breakdown

Weights74.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsQwen 3.5 122B A10B on AMD Instinct MI350X 288GB
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: 234.8 tok/s decode · 825ms TTFT (warm) · 587 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	Runs well	234.8 tok/s	450 ms	131K
Coding	S	Runs well	234.8 tok/s	825 ms	131K
Agentic Coding	S	Runs well	234.8 tok/s	1199 ms	131K
Reasoning	S	Runs well	234.8 tok/s	975 ms	131K
RAG	S	Runs well	234.8 tok/s	1499 ms	131K

Inference speed

Qwen 3.5 122B A10B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Qwen 3.5 122B A10B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~35 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?
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	34.7	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	28.9	Offloads
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	27.4	Offloads
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	21.4	Offloads
2× RX 7900 XTX 24GB	48 GB	Q4_K_M	11.3	Too big
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	10.0	Too big
2× RTX 4090 24GB	48 GB	Q4_K_M	7.6	Too big
RTX 5090 32GB	32 GB	Q4_K_M	7.2	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	7.0	Too big
2× RTX 3090 24GB	48 GB	Q4_K_M	6.5	Too big
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	6.4	Too big
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	5.9	Too big
4× RTX 3060 12GB	48 GB	Q4_K_M	5.7	Too big
RTX 4090 24GB	24 GB	Q4_K_M	4.6	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	4.2	Too big
RTX 3090 24GB	24 GB	Q4_K_M	4.0	Too big
RTX 4080 Super 16GB	16 GB	Q4_K_M	3.7	Too big
RTX 4070 12GB	12 GB	Q4_K_M	2.3	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

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 Qwen 3.5 122B A10B (122B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	47.6 GB	Low	A81
Q3_K_S	3	59.8 GB	Low	A82
NVFP4	4	68.3 GB	Medium	A83
Q4_K_M	4	74.4 GB	Medium	A83
Q5_K_M	5	87.8 GB	High	A84
Q6_K	6	100.0 GB	High	S85
Q8_0	8	130.5 GB	Very High	S88
F16Best for your GPU	16	250.1 GB	Maximum	S90

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 AMD Instinct MI350X 288GB can run

Model	Params	Grade	Decode	Capabilities
Qwen 3.5 397B A17B	397B	S	78.9 tok/s
Devstral 2 123B Instruct	123B	S	84.6 tok/s

Frequently asked questions

Can AMD Instinct MI350X 288GB run Qwen 3.5 122B A10B?

Yes, AMD Instinct MI350X 288GB can run Qwen 3.5 122B A10B with a S grade (Runs well). Expected decode speed: 234.8 tok/s.

How much VRAM does Qwen 3.5 122B A10B need?

Qwen 3.5 122B A10B (122B parameters) requires approximately 106.6 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 AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Qwen 3.5 122B A10B achieves approximately 234.8 tokens per second decode speed with a time-to-first-token of 825ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run Qwen 3.5 122B A10B for coding?

For coding workloads, Qwen 3.5 122B A10B on AMD Instinct MI350X 288GB receives a S grade with 234.8 tok/s and 131K context.

What context window can Qwen 3.5 122B A10B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, Qwen 3.5 122B A10B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB 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-instinct-mi350x-288gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: