Will It Run AI

Can Aya Expanse 32B run on RTX 4070 Ti Super 16GB?

YES — With Q2_K

C45Usable
Estimated from fit model

Aya Expanse 32B needs ~17.7 GB VRAM. RTX 4070 Ti Super 16GB has 16.0 GB. With Q2_K quantization, expect ~24 tok/s.

Runtime: OllamaCapacity: OffloadBandwidth: MediumStack: BasicBottleneck: Host offload
Share:

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.

Aya Expanse 32B at Q4_K_M needs 24.8 GB — too much for RTX 4070 Ti Super 16GB (16.0 GB). Runs at Q2_K (17.7 GB) with low quality.
Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 24.8 GB, exceeds 16.0 GB available
24.8 GB required16.0 GB available
155% VRAM needed

8.8 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

9.0 tok/s

TTFT

21610 ms

Safe context

4K

Memory

24.8 GB / 16.0 GB

Offload

40%

Memory breakdown

Weights19.5 GB
KV Cache2.4 GB
Runtime1.2 GB
Headroom1.6 GB

See how fast it feels

With memory offload — actual speed may be lower
See how fast it feelsAya Expanse 32B on RTX 4070 Ti Super 16GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API. When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed. Key benefits of running locally: - Full privacy: your prompts never leave your machine - No per-token cost or rate limits - Works offline once the model is downloaded - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb: Model size Q4 (4-bit) Q8 (8-bit) FP16 7B params ~4.3 GB ~7.5 GB ~14 GB 13B params ~7.9 GB ~13.9 GB ~26 GB 70B params ~42.7 GB ~74.9 GB ~140 GB Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 9.0 tok/s decode · 21.6s TTFT (warm) · 22 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

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.

Best improvement path

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

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

Increase host RAM if you keep offloading

This setup may need roughly 1.2 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatFToo heavy10.0 tok/s10597 ms4K
CodingFToo heavy9.0 tok/s21610 ms4K
Agentic CodingFToo heavy7.3 tok/s38314 ms4K
ReasoningFToo heavy9.0 tok/s25539 ms4K
RAGFToo heavy7.3 tok/s47892 ms4K

Quantization options

How Aya Expanse 32B (32B params) fits at each quantization level on RTX 4070 Ti Super 16GB (16.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
12.5 GB
LowF0
Q3_K_S
3
15.7 GB
LowF0
NVFP4
4
17.9 GB
MediumF0
Q4_K_M
4
19.5 GB
MediumF0
Q5_K_M
5
23.0 GB
HighF0
Q6_K
6
26.2 GB
HighF0
Q8_0
8
34.2 GB
Very HighF0
F16
16
65.6 GB
MaximumF0

Get started

Copy-paste commands to run Aya Expanse 32B on your machine.

Run

ollama run aya-expanse:32b

升级选项

能流畅运行 Aya Expanse 32B 的硬件

NVIDIARTX 3090 24GB经济之选
24 GB VRAM (+8)936 GB/s (+264)
C
Makes the model fit on the accelerator instead of staying completely out of reach.24 tok/s 解码

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

Raises estimated decode speed by about 167%.

~$1,499 MSRP

NVIDIARTX 4090 24GBNVIDIA 升级
24 GB VRAM (+8)1008 GB/s (+336)
C
Makes the model fit on the accelerator instead of staying completely out of reach.28 tok/s 解码

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

Raises estimated decode speed by about 211%.

~$1,599 MSRP

NVIDIARTX 5090 32GB最佳性价比
32 GB VRAM (+16)1792 GB/s (+1120)
B
Makes the model fit on the accelerator instead of staying completely out of reach.66.9 tok/s 解码

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.

~$1,999 MSRP

Frequently asked questions

Can RTX 4070 Ti Super 16GB run Aya Expanse 32B?

Yes, RTX 4070 Ti Super 16GB can run Aya Expanse 32B at Q2_K quantization (Very compromised (needs ~1.2 GB host RAM)). The recommended Q4_K_M requires 24.8 GB which exceeds available memory, but at Q2_K it needs only 17.7 GB. Expected decode speed: 24.1 tok/s.

How much VRAM does Aya Expanse 32B need?

Aya Expanse 32B (32B parameters) requires approximately 24.8 GB at Q4_K_M quantization. On RTX 4070 Ti Super 16GB, it fits at Q2_K using 17.7 GB.

What is the best quantization for Aya Expanse 32B?

The recommended quantization is Q4_K_M, but on RTX 4070 Ti Super 16GB the best fitting quantization is Q2_K, which uses 17.7 GB.

What speed will Aya Expanse 32B run at on RTX 4070 Ti Super 16GB?

On RTX 4070 Ti Super 16GB, Aya Expanse 32B achieves approximately 24.1 tokens per second decode speed with a time-to-first-token of 8038ms using Q2_K quantization.

Can RTX 4070 Ti Super 16GB run Aya Expanse 32B for coding?

For coding workloads, Aya Expanse 32B on RTX 4070 Ti Super 16GB receives a F grade with 9.0 tok/s and 4K context.

What context window can Aya Expanse 32B use on RTX 4070 Ti Super 16GB?

On RTX 4070 Ti Super 16GB, Aya Expanse 32B can safely use up to 5K tokens of context at Q2_K quantization. The model's official context limit is 8K, but available memory constrains the safe maximum.

What should I upgrade first if Aya Expanse 32B feels slow on RTX 4070 Ti Super 16GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

See all results for RTX 4070 Ti Super 16GBSee all hardware for Aya Expanse 32B
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/aya-expanse-32b-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: