Question 1

How much VRAM does t5gemma-ml-ml-ul2-it need?

Accepted Answer

t5gemma-ml-ml-ul2-it (2.2B) requires approximately 4.918155097961425 GB of VRAM at full precision (FP16), 2.5 GB at 8-bit quantization (Q8), and 1.2 GB at 4-bit quantization (Q4). The actual VRAM usage may be slightly higher due to KV cache and runtime overhead.

Question 2

What GPUs can run t5gemma-ml-ml-ul2-it?

Accepted Answer

We have 10 compatible GPUs indexed for t5gemma-ml-ml-ul2-it, including K80, L4, A40, A100 40GB, A10G and 5 more. Compatibility is determined by whether the GPU's VRAM can fit the model's memory footprint, potentially using quantization to reduce memory usage.

Question 3

What is the cheapest GPU to run t5gemma-ml-ml-ul2-it?

Accepted Answer

The cheapest GPU to run t5gemma-ml-ml-ul2-it in the cloud is the K80 at $0.18/hr. Other affordable options include L4 ($0.20/hr) and A40 ($0.44/hr). Prices reflect the lowest on-demand rate across cloud providers.

Question 4

Can t5gemma-ml-ml-ul2-it run on consumer hardware?

Accepted Answer

Yes, t5gemma-ml-ml-ul2-it can run on consumer GPUs like the RTX A6000 (48 GB VRAM) at full precision (FP16).

Question 5

What quantization options are available for t5gemma-ml-ml-ul2-it?

Accepted Answer

t5gemma-ml-ml-ul2-it supports the following quantization levels: FP16 (full precision): ~4.918155097961425 GB, Q8 (8-bit): ~2.5 GB, Q6 (6-bit): ~1.8 GB, Q4 (4-bit): ~1.2 GB. Lower quantization reduces VRAM usage at the cost of some quality loss. Q8 offers a good balance between quality and memory savings, while Q4 provides maximum compression.

GPU	VRAM	Best Quant	From	Rent
K80	12 GB	FP16	$0.18/hr
L4	24 GB	FP16	$0.20/hr
A40	48 GB	FP16	$0.44/hr	Rent
A100 40GB	40 GB	FP16	$0.93/hr	Rent
A10G	24 GB	FP16	$1.01/hr
RTX A6000	48 GB	FP16	$1.09/hr
A10	24 GB	FP16	$1.29/hr
A100 80GB PCIe	80 GB	FP16	$1.39/hr	Rent
A100 80GB	80 GB	FP16	$1.39/hr	Rent
H100 MEGA	80 GB	FP16	$1.80/hr	Rent

t5gemma-ml-ml-ul2-it

VRAM Requirements

Compatible GPUs

t5gemma-ml-ml-ul2-it FAQ

VRAM requirements for t5gemma-ml-ml-ul2-it at different quantization levels
Quantization	VRAM Required
FP16	4.9 GB
Q8	2.5 GB
Q6	1.8 GB
Q4	1.2 GB