Can Qwen 3.5 122B A10B run on AMD Instinct MI100 32GB?

NO — Won't Fit

F0Won't run

○Estimated from fit model

Qwen 3.5 122B A10B needs ~81.0 GB but AMD Instinct MI100 32GB only has 32.0 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) — 81.0 GB, exceeds 32.0 GB available

81.0 GB required32.0 GB available

253% VRAM needed

49.0 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

4.8 tok/s

TTFT

40221 ms

Safe context

Memory

81.0 GB / 32.0 GB

Offload

60%

Memory breakdown

Weights74.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom3.2 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsQwen 3.5 122B A10B on AMD Instinct MI100 32GB
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: 4.8 tok/s decode · 40.2s TTFT (warm) · 12 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 81.0 GB, but this setup only exposes 32.0 GB of usable VRAM.

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.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	4.8 tok/s	21939 ms	4K
Coding	F	Too heavy	4.8 tok/s	40221 ms	4K
Agentic Coding	F	Too heavy	4.8 tok/s	58503 ms	4K
Reasoning	F	Too heavy	4.8 tok/s	47533 ms	4K
RAG	F	Too heavy	4.8 tok/s	73128 ms	4K

Quantization options

How Qwen 3.5 122B A10B (122B params) fits at each quantization level on AMD Instinct MI100 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	47.6 GB	Low	F0
Q3_K_S	3	59.8 GB	Low	F0
NVFP4	4	68.3 GB	Medium	F0
Q4_K_M	4	74.4 GB	Medium	F0
Q5_K_M	5	87.8 GB	High	F0
Q6_K	6	100.0 GB	High	F0
Q8_0	8	130.5 GB	Very High	F0
F16	16	250.1 GB	Maximum	F0

Upgrade options

Hardware that runs Qwen 3.5 122B A10B well

AMD Instinct MI350X 288GBBudget pick

288 GB VRAM (+256)8000 GB/s (+6772)

Makes the model fit on the accelerator instead of staying completely out of reach.234.8 tok/s decode

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 MI300A 128GBBest value

128 GB VRAM (+96)5300 GB/s (+4072)

Makes the model fit on the accelerator instead of staying completely out of reach.149.2 tok/s decode

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.

~$12,000 MSRP

AMD Instinct MI250X 128GBAMD upgrade

128 GB VRAM (+96)3200 GB/s (+1972)

Makes the model fit on the accelerator instead of staying completely out of reach.100.3 tok/s decode

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.

~$15,000 MSRP

Frequently asked questions

See all results for AMD Instinct MI100 32GB See all hardware for Qwen 3.5 122B A10B

URL: https://willitrunai.com/can-run/qwen-3.5-122b-a10b-on-instinct-mi100-32gb

⇱ Qwen 3.5 122B A10B on AMD Instinct MI100 32GB? No — Alterna…

Can Qwen 3.5 122B A10B run on AMD Instinct MI100 32GB?

NO — Won't Fit

Choose the run profile you care about

Memory breakdown

See how fast it feels

What limits this setup

Best improvement path

Performance by workload

Quantization options

Hardware that runs Qwen 3.5 122B A10B well

Frequently asked questions