Can Qwen 3.6 35B A3B run on RTX 4070 Ti Super 16GB?

NO — Won't Fit

F0Won't run

Estimated from fit model

Qwen 3.6 35B A3B needs ~29.5 GB but RTX 4070 Ti Super 16GB only has 16.0 GB. Try a smaller quantization or lighter model.

Runtime: vLLMCapacity: No fitBandwidth: MediumStack: 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) — 29.5 GB, exceeds 16.0 GB available

29.5 GB required16.0 GB available

184% VRAM needed

13.5 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

10.8 tok/s

TTFT

17959 ms

Safe context

Memory

29.5 GB / 16.0 GB

Offload

50%

Memory breakdown

Weights21.3 GB

KV Cache4.1 GB

Runtime2.4 GB

Headroom1.6 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsQwen 3.6 35B A3B on RTX 4070 Ti Super 16GB
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: 10.8 tok/s decode · 18.0s TTFT (warm) · 27 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 29.5 GB, but this setup only exposes 16.0 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	12.5 tok/s	8415 ms	4K
Coding	F	Too heavy	10.8 tok/s	17959 ms	4K
Agentic Coding	F	Too heavy	8.2 tok/s	34373 ms	4K
Reasoning	F	Too heavy	10.8 tok/s	21225 ms	4K
RAG	F	Too heavy	8.2 tok/s	42966 ms	4K

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 RTX 4070 Ti Super 16GB (16.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	F0
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-Optionen

Hardware, die Qwen 3.6 35B A3B gut ausführt

RTX A6000 48GBGünstige Wahl

48 GB VRAM (+32)768 GB/s (+96)

Makes the model fit on the accelerator instead of staying completely out of reach.56.4 tok/s Dekodierung

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.

ca. $4,650 MSRP

RTX PRO 5000 Blackwell 48GBBestes Preis-Leistungs-Verhältnis

48 GB VRAM (+32)1344 GB/s (+672)

Makes the model fit on the accelerator instead of staying completely out of reach.109 tok/s Dekodierung

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.

ca. $4,999 MSRP

Quadro RTX 8000 48GBNVIDIA-Upgrade

48 GB VRAM (+32)

Makes the model fit on the accelerator instead of staying completely out of reach.44.8 tok/s Dekodierung

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.

ca. $5,800 MSRP

Frequently asked questions

Can RTX 4070 Ti Super 16GB run Qwen 3.6 35B A3B?

No, Qwen 3.6 35B A3B requires more memory than RTX 4070 Ti Super 16GB provides.

How much VRAM does Qwen 3.6 35B A3B need?

Qwen 3.6 35B A3B (35B parameters) requires approximately 29.5 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 RTX 4070 Ti Super 16GB?

On RTX 4070 Ti Super 16GB, Qwen 3.6 35B A3B achieves approximately 10.8 tokens per second decode speed with a time-to-first-token of 17959ms using Q4_K_M quantization.

Can RTX 4070 Ti Super 16GB run Qwen 3.6 35B A3B for coding?

For coding workloads, Qwen 3.6 35B A3B on RTX 4070 Ti Super 16GB receives a F grade with 10.8 tok/s and 4K context.

What context window can Qwen 3.6 35B A3B use on RTX 4070 Ti Super 16GB?

On RTX 4070 Ti Super 16GB, Qwen 3.6 35B A3B can safely use up to 4K tokens of context. 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 RTX 4070 Ti Super 16GB?

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.

See all results for RTX 4070 Ti Super 16GB 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-rtx-4070-ti-super-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: