No datasheet is linked because NVIDIA does not publish a product page for this part. It is an export-compliance variant sold into the Chinese market, and the addresses that would hold it return 404. Specifications for these variants circulate through server makers and resellers rather than through NVIDIA.

NVIDIA L20 48GB

Ada Lovelace PCIe 2024 Spec confidence: Official
FP8 (dense)
239
TFLOPS
FP32
60
TFLOPS
VRAM
48 GB
GDDR6
Bandwidth
864 GB/s
memory
TDP
275 W
217.5 TFLOPS/kW
Download datasheet

Performance

Peak theoretical throughput by precision type

INT8
8-bit integer
239 TOPS
sparse not published
FP8
8-bit floating point
239 TFLOPS
sparse not published
FP16
16-bit floating point
120 TFLOPS
sparse not published
BF16
Brain Float 16
120 TFLOPS
sparse not published
TF32
TensorFloat-32
60 TFLOPS
sparse not published
FP32
32-bit floating point
60 TFLOPS
0.869 TFLOPS/W FP8 at 275 W
0.435 TFLOPS/W FP16 at 275 W
0.217 TFLOPS/W FP32 at 275 W

The L20 48GB in the GPU landscape

Peak FP16 TFLOPS (dense) against TDP, single-GPU parts tracked by Flopper

06001,2001,8002,4003,0000 W250 W500 W750 W1000 W1250 W1500 WInstinct MI355XL20 48GB

Higher and further left is better: more half-precision throughput for less power.

Specifications

Architecture

Ada Lovelace

Form Factor

PCIe

Launch Year

2024

Memory

48 GB GDDR6

Bandwidth

864 GB/s

TDP

275 W

Max Power

~316 W

Spec Confidence

Official

Full Specifications

Memory
VRAM 48 GB
Memory Type GDDR6
Bandwidth 864 GB/s
Power & Thermal
TDP 275 W
Enterprise Features
Sparsity Yes
General
Form Factor PCIe
Architecture Ada Lovelace
Launch Year 2024

Datasheet & Resources

Flopper Datasheet

NVIDIA L20 48GB specifications, generated from our database. Printable.

NVIDIA Developer Documentation

Technical specs, programming guides

Browse

Data Provenance

Every figure traced to a source

Primary Source

Document
--
Publisher
NVIDIA
Published
--

Data Quality

Spec confidence
Official
Clock basis
Boost
Precisions tracked
6
Normalization
All values in TFLOPS

Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.

Browse GPU Cloud Providers

Similar GPUs

NVIDIA L40S 48GB

PCIe · 2023
FP32: 92 TFLOPS
Compare vs L40S

NVIDIA L40 48GB

PCIe · 2023
FP32: 91 TFLOPS
Compare vs L40

Frequently Asked Questions

How many TFLOPS does the NVIDIA L20 have?

The NVIDIA L20 delivers 59.8 TFLOPS for FP32 operations, 119.5 TFLOPS for FP16, and 239 TFLOPS for FP8 precision.

What is the power consumption of the NVIDIA L20?

The NVIDIA L20 has a TDP (Thermal Design Power) rating of 275 watts.

How much memory does the NVIDIA L20 have?

The NVIDIA L20 is equipped with 48 GB of VRAM with 864 GB/s memory bandwidth.

What architecture is the NVIDIA L20 based on?

The NVIDIA L20 is based on the Ada Lovelace architecture, launched in 2024.

Stay Updated on GPU Releases

Get notified when new GPUs are added or specifications are updated.

Loading verification...

No spam, unsubscribe anytime.

Back to GPUs