Support Matrix#

Hardware#

NVIDIA NIMs for large-language models should, but are not guaranteed to, run on any NVIDIA GPU, as long as the GPU has sufficient memory, or on multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory and CUDA compute capability > 7.0 (8.0 for bfloat16). Some model/GPU combinations, including vGPU, are optimized. See the following Supported Models section for further information.

Software#

  • Linux operating systems (Ubuntu 20.04 or later recommended)

  • NVIDIA Driver >= 535

  • NVIDIA Docker >= 23.0.1

GPUs#

The GPU listed in the following sections have the following specifications.

GPU

Family

Memory

H100

SXM/NVLink

80GB

A100

SXM/NVLink

80GB

L40S

PCIe

48GB

A10G

PCIe

24GB

Supported Models#

The following models are optimized using TRT-LLM and are available as pre-built, optimized engines on NGC and should use the Chat Completions Endpoint. For vGPU environment, the GPU memory values in the following sections refers to the total GPU memory, including the reserved GPU memory for vGPU setup.

Code Llama 13B Instruct#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP16

Throughput

2

24.63

H100

FP16

Latency

4

25.32

A100

FP16

Throughput

2

24.63

A100

FP16

Latency

4

25.31

L40S

FP16

Throughput

2

25.32

L40S

FP16

Latency

2

24.63

A10G

FP16

Throughput

4

25.32

A10G

FP16

Latency

8

26.69

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

Code Llama 34B Instruct#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP8

Throughput

1

6.57

H100

FP8

Latency

2

6.66

H100

FP16

Throughput

1

12.62

H100

FP16

Throughput LoRA

1

12.63

H100

FP16

Latency

2

12.93

A100

FP16

Throughput

1

15.54

A100

FP16

Throughput LoRA

1

12.63

A100

FP16

Latency

2

12.92

L40S

FP8

Throughput

1

6.57

L40S

FP8

Latency

2

6.64

L40S

FP16

Throughput

1

12.64

L40S

FP16

Throughput LoRA

1

12.65

L40S

FP16

Latency

2

12.95

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

Code Llama 70B Instruct#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

fp8

throughput

4

65.47

H100

fp8

Latency

8

66.37

H100

fp16

throughput

4

130.35

H100

fp16

latency

8

66.37

A100

fp16

throughput

4

130.35

A100

fp16

latency

8

132.71

A10G

fp16

throughput

8

132.69

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

(Meta) Llama 2 7B Chat#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP8

Throughput

1

6.57

H100

FP8

Latency

2

6.66

H100

FP16

Throughput

1

12.62

H100

FP16

Throughput LoRA

1

12.63

H100

FP16

Latency

2

12.93

A100

FP16

Throughput

1

15.54

A100

FP16

Throughput LoRA

1

12.63

A100

FP16

Latency

2

12.92

L40S

FP8

Throughput

1

6.57

L40S

FP8

Latency

2

6.64

L40S

FP16

Throughput

1

12.64

L40S

FP16

Throughput LoRA

1

12.65

L40S

FP16

Latency

2

12.95

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

(Meta) Llama 2 13B Chat#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP8

Latency

2

12.6

H100

FP16

Throughput

1

24.33

H100

FP16

Throughput LoRA

1

24.35

H100

FP16

Latency

2

24.71

A100

FP16

Throughput

1

24.34

A100

FP16

Throughput LoRA

1

24.37

A100

FP16

Latency

2

24.74

L40S

FP8

Throughput

1

12.49

L40S

FP8

Latency

2

12.59

L40S

FP16

Throughput

1

24.33

L40S

FP16

Latency

2

24.7

L40S

FP16

Throughput LoRA

1

24.37

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

(Meta) Llama 2 70B Chat#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP8

Throughput

2

65.08

H100

FP8

Latency

4

65.36

H100

FP16

Throughput

4

130.52

H100

FP16

Throughput LoRA

4

130.6

H100

FP16

Latency

8

133.18

A100

FP16

Throughput

4

130.52

A100

FP16

Throughput LoRA

4

130.5

A100

FP16

Latency

8

133.12

L40S

FP8

Throughput

4

63.35

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

Llama 3 SQLCoder 8B Instruct#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk space

H100

fp8

throughput

1

15

H100

fp8

latency

2

16.02

H100

fp16

throughput

1

8.52

H100

fp16

latency

2

8.61

A100

fp16

throughput

1

15

A100

fp16

latency

2

16.02

L40S

fp8

throughput

1

15

L40S

fp8

latency

2

16.02

L40S

fp16

throughput

1

8.53

L40S

fp16

latency

2

8.61

A10G

fp16

throughput

1

15

A10G

fp16

throughput

2

16.02

A10G

fp16

latency

4

18.06

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

Llama 3 Swallow 70B Instruct V0.1#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP8

Throughput

2

68.42

H100

FP8

Latency

4

69.3

H100

FP16

Throughput

2

137.7

H100

FP16

Latency

4

145.94

A100

FP16

Throughput

2

137.7

A100

FP16

Latency

2

137.7

L40S

FP8

Throughput

2

68.48

A10G

FP16

Throughput

4

145.93

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

Llama 3 Taiwan 70B Instruct#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP8

Throughput

2

68.42

H100

FP8

Latency

4

145.94

H100

FP16

Throughput

2

137.7

H100

FP16

Latency

4

137.7

A100

FP16

Throughput

2

137.7

A100

FP16

Latency

2

145.94

L40S

FP8

Throughput

2

68.48

A10G

FP16

Throughput

4

145.93

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

Llama 3.1 8B Base#

Optimized configurations#

Profile is for what the model is optimized.

GPU

Precision

Profile

# of GPUs

H100

BF16

Latency

2

H100

FP8

Latency

2

H100

BF16

Throughput

1

H100

FP8

Throughput

1

A100

BF16

Latency

2

A100

BF16

Throughput

1

L40S

BF16

Latency

2

L40S

BF16

Throughput

2

A10G

BF16

Latency

4

A10G

BF16

Throughput

2

Non-optimized configuration#

The GPU Memory and Disk Space values are in GB; Disk Space is for both the container and the model.

GPUs

GPU Memory

Precision

Disk Space

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

24

FP16

15

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

x

x

Llama 3.1 8B Instruct#

Optimized configurations#

Profile is for what the model is optimized.

GPU

Precision

Profile

# of GPUs

H100

BF16

Latency

2

H100

FP8

Latency

2

H100

BF16

Throughput

1

H100

FP8

Throughput

1

A100

BF16

Latency

2

A100

BF16

Throughput

1

L40S

BF16

Latency

2

L40S

BF16

Throughput

1

A10G

BF16

Latency

4

A10G

BF16

Throughput

2

Non-optimized configuration#

The GPU Memory and Disk Space values are in GB; Disk Space is for both the container and the model.

GPUs

GPU Memory

Precision

Disk Space

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

24

FP16

15

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

x

x

x

x

Llama 3.1 70B Instruct#

Optimized configurations#

Profile is for what the model is optimized.

GPU

Precision

Profile

# of GPUs

H100

FP8

Throughput

4

H100

FP8

Latency

8

H100

BF16

Throughput

4

H100

BF16

Latency

8

A100

BF16

Throughput

4

A100

BF16

Latency

8

L40S

BF16

Throughput

8

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

x

x

x

x

Llama 3.1 405B Instruct#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP8

Throughput

8

487

H100

FP16

Latency

8

797

A100

FP16

Latency

16

697

Non-optimized configuration#

The GPU Memory and Disk Space values are in GB; Disk Space is for both the container and the model.

GPUs

GPU Memory

Precision

Disk Space

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

240

FP16

100

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

x

x

x

Llama 3.1 Nemotron 70B Instruct#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk space

H100

fp8

throughput

2

68.18

H100

fp8

throughput

4

68.64

H100

fp8

latency

8

69.77

H100

fp16

throughput

4

137.94

H100

fp16

latency

8

146.41

A100

fp16

throughput

4

137.93

A100

fp16

latency

8

146.41

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

x

x

x

x

x

Meta Llama 3 8B Instruct#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP16

Throughput

1

28

H100

FP16

Latency

2

28

A100

FP16

Throughput

1

28

A100

FP16

Latency

2

28

L40S

FP8

Throughput

1

20.5

L40S

FP8

Latency

2

20.5

L40S

FP16

Throughput

1

28

A10G

FP16

Throughput

1

28

A10G

FP16

Latency

2

28

Non-optimized configuration#

The Disk Space values are in GB; Disk Space is for both the container and the model.

GPUs

GPU Memory

Precision

Disk Space

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

24

FP16

16

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

x

Meta Llama 3 70B Instruct#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP8

Throughput

4

82

H100

FP8

Latency

8

82

H100

FP16

Throughput

4

158

H100

FP16

Latency

8

158

A100

FP16

Throughput

4

158

Non-optimized configuration#

The GPU Memory and Disk Space values are in GB; Disk Space is for both the container and the model.

GPUs

GPU Memory

Precision

Disk Space

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

240

FP16

100

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

x

x

Mistral 7B Instruct V0.3#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP8

Throughput

1

7.06

H100

FP8

Latency

2

7.16

H100

FP16

Throughput

1

13.54

H100

FP16

Latency

2

13.82

A100

FP16

Throughput

1

13.54

A100

FP16

Latency

2

13.82

L40S

FP8

Throughput

1

7.06

L40S

FP8

Latency

2

7.14

L40S

FP16

Throughput

1

13.54

L40S

FP16

Latency

2

13.82

Non-optimized configuration#

The GPU Memory and Disk Space values are in GB; Disk Space is for both the container and the model.

GPUs

GPU Memory

Precision

Disk Space

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

24

FP16

16

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

Mistral NeMo Minitron 8B 8K Instruct#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

fp8

throughput

1

8.91

H100

fp8

latency

2

9.03

H100

fp16

throughput

1

15.72 GB

H100

fp16

latency

2

16.78 GB

A100

fp16

throughput

1

15.72

A100

fp16

latency

2

16.78

L40S

fp8

throughput

1

8.92

L40S

fp8

latency

2

9.02

L40S

fp16

throughput

1

15.72

L40S

fp16

latency

2

16.77

A10G

fp16

throughput

2

16.81

A10G

fp16

latency

4

15.72

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

Mistral NeMo 12B Instruct#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP8

Latency

2

13.82

H100

FP16

Throughput

1

23.35

H100

FP16

Latency

2

25.14

A100

FP16

Throughput

1

23.35

A100

FP16

Latency

2

25.14

L40S

FP8

Throughput

2

13.83

L40S

FP8

Latency

4

15.01

L40S

FP16

Throughput

2

25.14

L40S

FP16

Latency

4

28.71

A10G

FP16

Throughput

4

28.71

A10G

FP16

Latency

8

35.87

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

Mixtral 8x7B Instruct V0.1#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP8

Throughput

2

43.91

H100

FP8

Latency

4

44.07

H100

FP16

Throughput

2

87.35

H100

FP16

Latency

4

87.95

A100

FP16

Throughput

2

87.35

L40S

FP16

Throughput

4

87.95

Non-optimized configuration#

The GPU Memory and Disk Space values are in GB; Disk Space is for both the container and the model.

GPUs

GPU Memory

Precision

Disk Space

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

24

FP16

16

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

x

Mixtral 8x22B Instruct V0.1#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP8

Throughput

8

132.61

H100

FP8

Latency

8

132.56

H100

int8wo

Throughput

8

134.82

H100

int8wo

Latency

8

132.31

H100

FP16

Throughput

8

265.59

A100

FP16

Throughput

8

265.7

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

x

Nemotron 4 340B Instruct#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP16

Latency

16

627

A100

FP16

Latency

16

627

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

Nemotron 4 340B Instruct 128K#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP16

Latency

16

637

A100

FP16

Latency

16

637

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

Nemotron 4 340B Reward#

Optimized configurations#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

FP16

Latency

16

637

A100

FP16

Latency

16

637

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

x

x

Phi 3 Mini 4K Instruct#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

fp8

Throughput

1

3.8

H100

fp16

Throughput

1

7.14

A100

fp16

Throughput

1

7.14

L40S

fp8

Throughput

1

3.8

L40S

fp16

Throughput

1

7.14

A10G

fp16

Throughput

1

7.14

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x

Phind Codellama 34B V2#

Profile is for what the model is optimized; the Disk Space is for both the container and the model and the values are in GB.

GPU

Precision

Profile

# of GPUs

Disk Space

H100

fp8

throughput

2

32.17

H100

fp8

latency

4

32.41

H100

fp16

throughput

2

63.48

H100

fp16

latency

4

64.59

A100

fp16

throughput

2

63.48

A100

fp16

latency

4

64.59

L40S

fp8

throughput

4

32.43

L40S

fp16

throughput

4

64.58

A10G

fp16

throughput

4

64.58

A10G

fp16

latency

8

66.8

Non-optimized configuration#

Any NVIDIA GPU should be, but is not guaranteed to be, able to run this model with sufficient GPU memory or multiple, homogeneous NVIDIA GPUs with sufficient aggregate memory, compute capability >= 7.0 (8.0 for bfloat16), and at least one GPU with 95% or greater free memory.

Supported Releases#

This model is supported in the following releases.

1

1.0

1.0.0

1.0.1

1.0.3

1.1

1.1.0

1.1.1

1.1.2

1.2

1.2.0

1.2.1

1.2.3

x