Question 1

What AI models can run on T4?

Accepted Answer

The T4 (16 GB VRAM) can run models including MediPhi-Clinical, MediPhi-MedWiki, Llama-2-7b, Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8, Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8 and more — 10 compatible models indexed so far. Compatible models are determined by whether the model's memory footprint fits within the GPU's 16 GB VRAM, potentially using quantization (Q8, Q6, or Q4) to reduce memory usage.

Question 2

What is the cheapest cloud option for T4?

Accepted Answer

The cheapest on-demand option for the T4 is Google Cloud at $0.35/hr (). Spot/preemptible pricing is available at $0.14/hr. We track pricing across 147 providers to help you find the best deal.

Question 3

Is T4 good for fine-tuning?

Accepted Answer

The T4 can handle fine-tuning with some constraints. With 16 GB of VRAM, it's suitable for LoRA/QLoRA fine-tuning of models up to ~7B parameters. Full fine-tuning is limited to smaller models (~1-3B parameters). Techniques like gradient checkpointing and mixed precision help maximize what fits.

Question 4

How much VRAM does T4 have?

Accepted Answer

The T4 has 16 GB of VRAM (GDDR6). It also offers 320 GB/s memory bandwidth, 65.1 TFLOPS of FP16 compute.

Question 5

What quantization formats work on T4?

Accepted Answer

The T4 supports the following quantization formats: FP16 (full precision), Q8 (8-bit), Q6 (6-bit), Q4 (4-bit). FP16 works for models up to ~3B parameters. Q4 quantization can fit models requiring up to ~64 GB at FP16 into 16 GB.

Provider	On-demand	Spot	Actions
Google Cloud	$0.350/hr	$0.098/hr	—
Microsoft Azure	$0.526/hr	$0.058/hr	—
Amazon Web Services	$0.526/hr	$0.109/hr	—

T4

Specifications

Cloud pricing

Compatible models

Compare this GPU

Frequently asked questions

VRAM	16 GB
Memory type	GDDR6
Bandwidth	320 GB/s
FP16 TFLOPS	65.1
FP8 support	No

T4