Can Qwen 3.6 35B A3B run on NVIDIA L40S 48GB?

YES — Runs Great

S99Excellent

Estimated from fit model

Qwen 3.6 35B A3B needs ~32.9 GB VRAM. NVIDIA L40S 48GB has 48.0 GB. With Q4_K_M quantization, expect ~86 tok/s.

Runtime: SGLangCapacity: 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) — 32.9 GB, 85.6 tok/s, Runs well

32.9 GB required48.0 GB available

69% VRAM used

Fit status

Runs well

Decode

85.6 tok/s

TTFT

2261 ms

Safe context

75K

Memory

32.9 GB / 48.0 GB

Memory breakdown

Weights21.3 GB

KV Cache4.1 GB

Runtime2.6 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsQwen 3.6 35B A3B on NVIDIA L40S 48GB
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: 85.6 tok/s decode · 2.3s TTFT (warm) · 214 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	85.6 tok/s	1233 ms	75K
Coding	S	Runs well	85.6 tok/s	2261 ms	75K
Agentic Coding	S	Runs well	85.6 tok/s	3288 ms	75K
Reasoning	S	Runs well	85.6 tok/s	2672 ms	75K
RAG	S	Runs well	85.6 tok/s	4110 ms	75K

Inference speed

Qwen 3.6 35B A3B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Qwen 3.6 35B A3B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~153 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?
RTX 5090 32GB	32 GB	Q4_K_M	152.6	Offloads
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	70.8	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	59.0	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	55.9	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	43.7	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	43.7	Fits
RTX 4090 24GB	24 GB	Q4_K_M	34.1	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	30.8	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	30.5	Fits
RTX 3090 24GB	24 GB	Q4_K_M	29.2	Too big
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	28.0	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	26.7	Tight
RTX 4080 Super 16GB	16 GB	Q4_K_M	12.2	Too big
RTX 4070 12GB	12 GB	Q4_K_M	5.5	Too big
RTX 3060 12GB	12 GB	Q4_K_M	3.4	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.9	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 3.6 35B A3B (35B params) fits at each quantization level on NVIDIA L40S 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	S86
Q3_K_S	3	17.2 GB	Low	S88
NVFP4	4	19.6 GB	Medium	S88
Q4_K_M	4	21.3 GB	Medium	S89
Q5_K_M	5	25.2 GB	High	S90
Q6_K	6	28.7 GB	High	S90
Q8_0Best for your GPU	8	37.5 GB	Very High	S90
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 L40S 48GB run Qwen 3.6 35B A3B?

Yes, NVIDIA L40S 48GB can run Qwen 3.6 35B A3B with a S grade (Runs well). Expected decode speed: 85.6 tok/s.

How much VRAM does Qwen 3.6 35B A3B need?

Qwen 3.6 35B A3B (35B parameters) requires approximately 32.9 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 L40S 48GB?

On NVIDIA L40S 48GB, Qwen 3.6 35B A3B achieves approximately 85.6 tokens per second decode speed with a time-to-first-token of 2261ms using Q4_K_M quantization.

Can NVIDIA L40S 48GB run Qwen 3.6 35B A3B for coding?

For coding workloads, Qwen 3.6 35B A3B on NVIDIA L40S 48GB receives a S grade with 85.6 tok/s and 75K context.

What context window can Qwen 3.6 35B A3B use on NVIDIA L40S 48GB?

On NVIDIA L40S 48GB, Qwen 3.6 35B A3B can safely use up to 75K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for NVIDIA L40S 48GB 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-l40s-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: