OpenModelsHQ

L4

NVIDIA · Data center GPU

L4 has 24 GB of memory and 300 GB/s of memory bandwidth. 360 open models in our directory fit at 4-bit.

Usable for models, before runtime overhead
24GB
Listed memory, before overhead
Total memory
24 GB
Bandwidth
300 GB/s
Models that fit at 4-bit
360
Within 21.6 GB, 90% of usable

Planning a multi-GPU deployment? Check NVLink domains and network topology as well as memory fit. A GPU specification alone does not establish the interconnect in a server or cloud allocation.

What fits by category
On L4 at 4-bit, 360 models fit, 21 are tight and 110 are too big, across 6 categories. Fits means the estimate is within 90% of usable memory; tight is between 90% and 100%. Models without a published size are left out.
What fits by category: data
CategoryFitsTightToo bigTotal
LLM1831681280
Vision75328106
Image221124
Video220022
Speech391040
Embedding190019

Largest open models that fit at 4-bit

See all 360 in the table

A model fits when its 4-bit memory estimate (8k context) stays within 90% of usable memory, about 21.6 GB here. Showing the 30 largest of 360.

These are memory checks, not speed or runtime compatibility results.

Compared with

All hardware
HardwareTotal memoryUsable for modelsBandwidth
L4This device
24 GBUp to 24 GB300 GB/s
48 GBUp to 48 GB864 GB/s
80 GBUp to 80 GB2,039 GB/s
80 GBUp to 80 GB3,350 GB/s

Capacity and bandwidth answer different questions: memory decides what fits, bandwidth drives how fast it runs.

Launch dates, useful-life evidence and ownership cost scenarios