Models#

The following LLMs are available as NIMs. Click the model name to view the hardware requirements for each model. Click the Catalog Page to get additional information about the model. For more information, refer to Supported Models.

Model (Hardware Requirements)

Organization

Organization/Model ID (Catalog Page)

Versions Supported

LoRA Support

Tool Calling Support

Parallel Tool Calling Support

Suffix Support

Code Llama 13B Instruct

Meta

meta/codellama-13b-instruct

1.0, 1.2, 1.2.3

-

-

-

Yes

Code Llama 34B Instruct

Meta

meta/codellama-34b-instruct

1.0, 1.2, 1.2.3

-

-

-

Yes

Code Llama 70B Instruct

Meta

meta/codellama-70b-instruct

1.0, 1.2, 1.2.3

-

-

-

Yes

DeepSeek R1

DeepSeek

deepseek-ai/deepseek-r1

1.7, 1.7.3

No

No

No

Yes

DeepSeek R1 Distill Llama 8B

DeepSeek

deepseek-ai/deepseek-r1-distill-llama-8b

1.5

-

-

-

Yes

DeepSeek R1 Distill Llama 70B

DeepSeek

deepseek-ai/deepseek-r1-distill-llama-70b

1.5

-

-

-

Yes

DeepSeek R1 Distill Llama 8B RTX

DeepSeek

deepseek-ai/deepseek-r1-distill-llama-8b

1.8

-

-

-

Yes

DeepSeek-R1-Distill-Qwen-32B

DeepSeek

deepseek-ai/deepseek-r1-distill-qwen-32b

1.8

-

-

-

Yes

Gemma 2 2B

Google

google/gemma-2-2b-instruct

1.4

-

-

-

No

Gemma 2 9B

Google

google/gemma-2-9b-it

1.4.0

-

-

-

-

(Meta) Llama 2 7B Chat

Meta

meta/llama-2-7b-chat

1.0, 1.0.3

-

-

-

No

(Meta) Llama 2 13B Chat

Meta

meta/llama-2-13b-chat

1.0, 1.0.3

H100, A100, L40S

-

-

No

(Meta) Llama 2 70B Chat

Meta

meta/llama-2-70b-chat

1.0, 1.0.3

-

-

-

No

Llama 3 SQLCoder 8B

Meta

defog/llama-3-sqlcoder-8b

1.2.3

-

-

-

No

Llama 3 Swallow 70B Instruct V0.1

Meta

tokyotech-llm/llama-3-swallow-70b-instruct-v0.1

1.0, 1.2, 1.1.2

-

-

-

No

Llama 3 Taiwan 70B Instruct

Meta

yentinglin/llama-3-taiwan-70b-instruct

1.0, 1.1, 1.1.2

-

-

-

No

Llama 3.1 8B Base

Meta

meta/llama-3.1-8b-base

1.0, 1.1, 1.1.1, 1.1.2

-

Yes

Yes

No

Llama 3.1 8B Instruct

Meta

meta/llama-3.1-8b-instruct

1.0, 1.1, 1.1.1, 1.1.2, 1.2, 1.2.3, 1.3, 1.3.3, 1.8, 1.8.3, 1.8.4

Yes

Yes

Yes

No

Llama 3.1 8B Instruct RTX

Meta

meta/llama-3.1-8b-instruct

1.8

-

Yes

Yes

No

Llama 3.1 70B Instruct

Meta

meta/llama-3.1-70b-instruct

1.0, 1.1, 1.1.1, 1.1.2, 1.2, 1.2.1, 1.3, 1.8.3, 1.8.4, 1.8.5

Yes

Yes

Yes

No

Llama 3.1 405B Instruct

Meta

meta/llama-3.1-405b-instruct

1.0, 1.1, 1.1.2, 1.2, 1.3

-

Yes

Yes

No

Llama 3.1 Nemotron Nano 8B V1

NVIDIA

nvidia/llama-3.1-nemotron-nano-8b-v1

1.6.0, 1.8.3

No

-

-

No

Llama 3.1 Nemotron Ultra 253B V1

NVIDIA

nvidia/llama-3.1-nemotron-ultra-253b-v1

1.8.4

No

Yes

-

No

Llama 3.1 Nemotron 70B Instruct

NVIDIA

nvidia/llama-3.1-nemotron-70b-instruct

1.0, 1.1, 1.1.1, 1.2, 1.2.1, 1.2.3

-

-

-

No

Llama 3.1 Swallow 8B Instruct v0.1

Meta

tokyotech-llm/llama-3.1-swallow-8b-instruct-v0.1

1.3

-

-

-

No

Llama 3.1 Swallow 70B Instruct v0.1

Meta

tokyotech-llm/llama-3.1-swallow-70b-instruct-v0.1

1.3

-

-

-

No

Llama 3.2 1B Instruct

Meta

meta/llama-3.2-1b-instruct

1.6.0, 1.8.1, 1.8.3, 1.8.5

Yes

Yes

-

No

Llama 3.2 3B Instruct

Meta

meta/llama-3.2-3b-instruct

1.6.0, 1.8.3, 1.8.4, 1.8.5

Yes

Yes

No

No

Llama 3.3 70B Instruct

Meta

meta/llama-3.3-70b-instruct

1.5.2, 1.8.2, 1.8.3, 1.8.4, 1.8.5

Yes

Yes

No

No

Llama 3.3 Nemotron Super 49B V1

NVIDIA

nvidia/llama-3.3-nemotron-super-49b-v1

1.8.3, 1.8.4, 1.8.5

Yes

Yes

-

No

Meta Llama 3 8B Instruct

Meta

meta/llama3-8b-instruct

1.0, 1.0.3

-

-

-

No

Meta Llama 3 70B Instruct

Meta

meta/llama3-70b-instruct

1.0, 1.0.1, 1.0.3

-

-

-

No

Mistral 7B Instruct V0.3

Mistral

mistralai/mistral-7b-instruct-v0.3

1.0, 1.1, 1.1.2, 1.3

Hugging Face, NeMo Formats

Yes

Yes

No

Mistral NeMo 12B Instruct RTX

Mistral

nv-mistralai/mistral-nemo-12b-instruct

1.8.0-RTX, 1.8.4-RTX

-

-

-

No

Mistral NeMo 12B Instruct

Mistral

nv-mistralai/mistral-nemo-12b-instruct

1.0, 1.2, 1.2.3

-

-

-

No

Mistral NeMo Minitron 8B 8K Instruct

Mistral

nv-mistralai/mistral-nemo-minitron-8b-8k-instruct

1.2.3

Yes

-

-

No

Mixtral 8x7B Instruct V0.1

Mistral

mistralai/mixtral-8x7b-instruct-v01

1.0, 1.2, 1.2.1, 1.3

Hugging Face, NeMo Formats

No

No

No

Mixtral 8x22B Instruct V0.1

Mistral

mistralai/mixtral-8x22b-instruct-v01

1.0, 1.2, 1.2.3

-

Yes

Yes

No

Nemotron 4 340B Instruct

NVIDIA

nvidia/nemotron-4-340b-instruct

1.0, 1.1, 1.1.2

-

-

-

No

Nemotron 4 340B Reward

NVIDIA

nvidia/nemotron-4-340b-reward

1.0, 1.2

-

Yes

Yes

No

Phi 3 Mini 4K Instruct

Microsoft

microsoft/phi-3-mini-4k-instruct

1.2.3

-

-

-

No

Phind Codellama 34B V2 Instruct

Microsoft

phind/phind-codellama-34b-v2-instruct

1.2.3

-

-

-

No

Qwen2.5 7B Instruct

Alibaba Cloud

qwen/qwen-2.5-7b-instruct

1.4.0

-

-

-

No

StarCoder2 7B

BigCode

bigcode/starcoder2-7b

1.8

-

-

-

Yes

StarCoderBase 15.5B

BigCode

bigcode/starcoderbase-15b

1.5

-

-

-

Yes