Can Qwen 3.6 35B A3B run on RX 7900 XT 20GB?

NO — Won't Fit

F0Won't run

○Estimated from fit model

Qwen 3.6 35B A3B needs ~29.9 GB but RX 7900 XT 20GB only has 20.0 GB. Try a smaller quantization or lighter model.

Runtime: vLLMCapacity: No fitBandwidth: HighStack: OptimizedBottleneck: 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) — 29.9 GB, exceeds 20.0 GB available

29.9 GB required20.0 GB available

150% VRAM needed

9.9 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

15.0 tok/s

TTFT

12937 ms

Safe context

Memory

29.9 GB / 20.0 GB

Offload

30%

Memory breakdown

Weights21.3 GB

KV Cache4.1 GB

Runtime2.4 GB

Headroom2.0 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsQwen 3.6 35B A3B on RX 7900 XT 20GB
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: 15.0 tok/s decode · 12.9s TTFT (warm) · 37 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 29.9 GB, but this setup only exposes 20.0 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	17.4 tok/s	6075 ms	4K
Coding	F	Too heavy	15.0 tok/s	12937 ms	4K
Agentic Coding	F	Too heavy	11.4 tok/s	24676 ms	4K
Reasoning	F	Too heavy	15.0 tok/s	15290 ms	4K
RAG	F	Too heavy	11.4 tok/s	30845 ms	4K

Quantization options

How Qwen 3.6 35B A3B (35B params) fits at each quantization level on RX 7900 XT 20GB (20.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_KBest for your GPU	2	13.7 GB	Low	S92
Q3_K_S	3	17.2 GB	Low	F0
NVFP4	4	19.6 GB	Medium	F0
Q4_K_M	4	21.3 GB	Medium	F0
Q5_K_M	5	25.2 GB	High	F0
Q6_K	6	28.7 GB	High	F0
Q8_0	8	37.5 GB	Very High	F0
F16	16	71.8 GB	Maximum	F0

Upgrade options

Hardware that runs Qwen 3.6 35B A3B well

Radeon Pro W7900 48GBBudget pick

48 GB VRAM (+28)864 GB/s (+64)

Makes the model fit on the accelerator instead of staying completely out of reach.49.2 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.

~$3,999 MSRP

Radeon PRO W7900 DS 48GBBest value

48 GB VRAM (+28)864 GB/s (+64)

Makes the model fit on the accelerator instead of staying completely out of reach.49.2 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.

~$3,999 MSRP

AMD Instinct MI350X 288GBAMD upgrade

288 GB VRAM (+268)8000 GB/s (+7200)

Makes the model fit on the accelerator instead of staying completely out of reach.564 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

Frequently asked questions

See all results for RX 7900 XT 20GB See all hardware for Qwen 3.6 35B A3B

URL: https://willitrunai.com/can-run/qwen-3.6-35b-a3b-on-rx-7900-xt-20gb

⇱ Qwen 3.6 35B A3B on RX 7900 XT 20GB? No — Alternatives

Can Qwen 3.6 35B A3B run on RX 7900 XT 20GB?

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 3.6 35B A3B well

Frequently asked questions