Can Qwen 3.5 397B A17B run on RTX PRO 6000 Blackwell Workstation Edition 96GB?

NO — Won't Fit

F0Won't run

○Estimated from fit model

Qwen 3.5 397B A17B needs ~255.5 GB but RTX PRO 6000 Blackwell Workstation Edition 96GB only has 96.0 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) — 255.5 GB, exceeds 96.0 GB available

255.5 GB required96.0 GB available

266% VRAM needed

159.5 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

3.1 tok/s

TTFT

63457 ms

Safe context

Memory

255.5 GB / 96.0 GB

Offload

60%

Memory breakdown

Weights242.2 GB

KV Cache2.9 GB

Runtime0.9 GB

Headroom9.6 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsQwen 3.5 397B A17B on RTX PRO 6000 Blackwell Workstation Edition 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: 3.1 tok/s decode · 63.5s TTFT (warm) · 8 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 255.5 GB, but this setup only exposes 96.0 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	3.1 tok/s	34613 ms	4K
Coding	F	Too heavy	2.8 tok/s	69406 ms	4K
Agentic Coding	F	Too heavy	3.1 tok/s	92301 ms	4K
Reasoning	F	Too heavy	3.1 tok/s	74995 ms	4K
RAG	F	Too heavy	3.1 tok/s	115376 ms	4K

Quantization options

How Qwen 3.5 397B A17B (397B params) fits at each quantization level on RTX PRO 6000 Blackwell Workstation Edition 96GB (96.0 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

Upgrade options

Hardware that runs Qwen 3.5 397B A17B well

AMD Instinct MI350X 288GBBudget pick

288 GB VRAM (+192)8000 GB/s (+6208)

Makes the model fit on the accelerator instead of staying completely out of reach.78.9 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 MI325X 256GBBest value

256 GB VRAM (+160)6000 GB/s (+4208)

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