Can Qwen 3.6 35B A3B run on NVIDIA A100 40GB?

YES — Runs Great

S99Excellent

Estimated from fit model

Qwen 3.6 35B A3B needs ~31.9 GB VRAM. NVIDIA A100 40GB has 40.0 GB. With Q4_K_M quantization, expect ~126 tok/s.

Runtime: vLLMCapacity: RoomyBandwidth: HighStack: OptimizedBottleneck: 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) — 31.9 GB, 126.2 tok/s, Runs well

31.9 GB required40.0 GB available

80% VRAM used

Fit status

Runs well

Decode

126.2 tok/s

TTFT

1535 ms

Safe context

48K

Memory

31.9 GB / 40.0 GB

Memory breakdown

Weights21.3 GB

KV Cache4.1 GB

Runtime2.4 GB

Headroom4.0 GB

See how fast it feels

See how fast it feelsQwen 3.6 35B A3B on NVIDIA A100 40GB
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: 126.2 tok/s decode · 1.5s TTFT (warm) · 315 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	126.2 tok/s	837 ms	48K
Coding	S	Runs well	126.2 tok/s	1535 ms	48K
Agentic Coding	S	Tight fit	126.2 tok/s	2232 ms	48K
Reasoning	S	Runs well	126.2 tok/s	1814 ms	48K
RAG	S	Tight fit	126.2 tok/s	2790 ms	48K

Quantization options

How Qwen 3.6 35B A3B (35B params) fits at each quantization level on NVIDIA A100 40GB (40.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	S88
Q3_K_S	3	17.2 GB	Low	S89
NVFP4	4	19.6 GB	Medium	S91
Q4_K_M	4	21.3 GB	Medium	S91
Q5_K_M	5	25.2 GB	High	S91
Q6_KBest for your GPU	6	28.7 GB	High	S90
Q8_0	8	37.5 GB	Very High	F0
F16	16	71.8 GB	Maximum	F0

Get started

Copy-paste commands to run Qwen 3.6 35B A3B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "Qwen/Qwen3.6-35B-A3B" \
  --hf-file "Qwen3.6-35B-A3B-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Frequently asked questions

Can NVIDIA A100 40GB run Qwen 3.6 35B A3B?

Yes, NVIDIA A100 40GB can run Qwen 3.6 35B A3B with a S grade (Runs well). Expected decode speed: 126.2 tok/s.

How much VRAM does Qwen 3.6 35B A3B need?

Qwen 3.6 35B A3B (35B parameters) requires approximately 31.9 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 3.6 35B A3B?

The recommended quantization for Qwen 3.6 35B A3B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 3.6 35B A3B run at on NVIDIA A100 40GB?

On NVIDIA A100 40GB, Qwen 3.6 35B A3B achieves approximately 126.2 tokens per second decode speed with a time-to-first-token of 1535ms using Q4_K_M quantization.

Can NVIDIA A100 40GB run Qwen 3.6 35B A3B for coding?

For coding workloads, Qwen 3.6 35B A3B on NVIDIA A100 40GB receives a S grade with 126.2 tok/s and 48K context.

What context window can Qwen 3.6 35B A3B use on NVIDIA A100 40GB?

On NVIDIA A100 40GB, Qwen 3.6 35B A3B can safely use up to 48K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for NVIDIA A100 40GB See all hardware for Qwen 3.6 35B A3B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-3.6-35b-a3b-on-a100-40gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

126.2 tok/s

837 ms

48K

Coding

Runs well

126.2 tok/s

1535 ms

48K

Agentic Coding

Tight fit

126.2 tok/s

2232 ms

48K

Reasoning

Runs well

126.2 tok/s

1814 ms

48K

RAG

Tight fit

126.2 tok/s

2790 ms

48K

Quantization options

How Qwen 3.6 35B A3B (35B params) fits at each quantization level on NVIDIA A100 40GB (40.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	S88
Q3_K_S	3	17.2 GB	Low	S89
NVFP4	4	19.6 GB	Medium	S91
Q4_K_M	4	21.3 GB	Medium	S91
Q5_K_M	5	25.2 GB	High	S91
Q6_KBest for your GPU	6	28.7 GB	High	S90
Q8_0	8	37.5 GB	Very High	F0
F16	16	71.8 GB	Maximum	F0

Frequently asked questions

Can NVIDIA A100 40GB run Qwen 3.6 35B A3B?

Yes, NVIDIA A100 40GB can run Qwen 3.6 35B A3B with a S grade (Runs well). Expected decode speed: 126.2 tok/s.

How much VRAM does Qwen 3.6 35B A3B need?

Qwen 3.6 35B A3B (35B parameters) requires approximately 31.9 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 3.6 35B A3B?

The recommended quantization for Qwen 3.6 35B A3B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 3.6 35B A3B run at on NVIDIA A100 40GB?

On NVIDIA A100 40GB, Qwen 3.6 35B A3B achieves approximately 126.2 tokens per second decode speed with a time-to-first-token of 1535ms using Q4_K_M quantization.

Can NVIDIA A100 40GB run Qwen 3.6 35B A3B for coding?

For coding workloads, Qwen 3.6 35B A3B on NVIDIA A100 40GB receives a S grade with 126.2 tok/s and 48K context.

What context window can Qwen 3.6 35B A3B use on NVIDIA A100 40GB?

On NVIDIA A100 40GB, Qwen 3.6 35B A3B can safely use up to 48K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.