Can Qwen 3.6 35B A3B run on Tesla P40 24GB?

YES — With Q2_K

S92Excellent

Estimated from fit model

Qwen 3.6 35B A3B needs ~22.6 GB VRAM. Tesla P40 24GB has 24.0 GB. With Q2_K quantization, expect ~26 tok/s.

Runtime: vLLMCapacity: TightBandwidth: LowStack: 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.

Qwen 3.6 35B A3B at Q4_K_M needs 30.3 GB — too much for Tesla P40 24GB (24.0 GB). Runs at Q2_K (22.6 GB) with low quality.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 30.3 GB, exceeds 24.0 GB available

30.3 GB required24.0 GB available

126% VRAM needed

6.3 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

8.7 tok/s

TTFT

22381 ms

Safe context

Memory

30.3 GB / 24.0 GB

Offload

20%

Memory breakdown

Weights21.3 GB

KV Cache4.1 GB

Runtime2.4 GB

Headroom2.4 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsQwen 3.6 35B A3B on Tesla P40 24GB
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: 8.7 tok/s decode · 22.4s TTFT (warm) · 22 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Older PCIe generation

PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.

Best improvement path

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	10.1 tok/s	10464 ms	4K
Coding	F	Too heavy	8.7 tok/s	22381 ms	4K
Agentic Coding	F	Too heavy	6.5 tok/s	43040 ms	4K
Reasoning	F	Too heavy	8.7 tok/s	26451 ms	4K
RAG	F	Too heavy	6.5 tok/s	53800 ms	4K

Quantization options

How Qwen 3.6 35B A3B (35B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	S92
Q3_K_SBest for your GPU	3	17.2 GB	Low	S92
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

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

Opciones de mejora

Hardware que ejecuta bien Qwen 3.6 35B A3B

RTX A6000 48GBOpción económica

48 GB VRAM (+24)768 GB/s (+422)

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.56.4 tok/s decodificación

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.

Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.

~$4,650 MSRP

RTX PRO 5000 Blackwell 48GBMejor relación calidad-precio

48 GB VRAM (+24)1344 GB/s (+998)

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.109 tok/s decodificación

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.

Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.

~$4,999 MSRP

NVIDIA L40 48GBMejora NVIDIA

48 GB VRAM (+24)864 GB/s (+518)

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.65.1 tok/s decodificación

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.

Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.

~$5,500 MSRP

Frequently asked questions

Can Tesla P40 24GB run Qwen 3.6 35B A3B?

Yes, Tesla P40 24GB can run Qwen 3.6 35B A3B at Q2_K quantization (Tight fit). The recommended Q4_K_M requires 30.3 GB which exceeds available memory, but at Q2_K it needs only 22.6 GB. Expected decode speed: 26.2 tok/s.

How much VRAM does Qwen 3.6 35B A3B need?

Qwen 3.6 35B A3B (35B parameters) requires approximately 30.3 GB at Q4_K_M quantization. On Tesla P40 24GB, it fits at Q2_K using 22.6 GB.

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

The recommended quantization is Q4_K_M, but on Tesla P40 24GB the best fitting quantization is Q2_K, which uses 22.6 GB.

What speed will Qwen 3.6 35B A3B run at on Tesla P40 24GB?

On Tesla P40 24GB, Qwen 3.6 35B A3B achieves approximately 26.2 tokens per second decode speed with a time-to-first-token of 7386ms using Q2_K quantization.

Can Tesla P40 24GB run Qwen 3.6 35B A3B for coding?

For coding workloads, Qwen 3.6 35B A3B on Tesla P40 24GB receives a F grade with 8.7 tok/s and 4K context.

What context window can Qwen 3.6 35B A3B use on Tesla P40 24GB?

On Tesla P40 24GB, Qwen 3.6 35B A3B can safely use up to 22K tokens of context at Q2_K quantization. The model's official context limit is 262K, but available memory constrains the safe maximum.

What should I upgrade first if Qwen 3.6 35B A3B feels slow on Tesla P40 24GB?

Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

See all results for Tesla P40 24GB 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-tesla-p40-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: