Mistral-7B-Instruct-v0.3

NVIDIA

Container

NVIDIA

Mistral-7B-Instruct-v0.3

This container houses the Mistral-7B-Instruct-v0.3, a large language model fine-tuned for instruction-based tasks. An improved version of Mistral-7B-v0.3, it is designed to be easily fine-tuned to achieve compelling performance.

NVIDIA NIM

Join or Subscribe to get accessSubscribe to the product below to access this premium content:

NVIDIA Developer ProgramJoin the Developer Program for access to free tools, support, and tech resources.

Get Access

NVIDIA AI EnterpriseAccelerate your AI agent development

Subscribe Now

Note: You can gain access to hundreds more GPU-optimized artifacts by creating a free NGC account.

Already Subscribed?Log in

NIM MetadataTo verify your workspace, run the Verify CLI locally and compare the generated hash with the NGC-published hash shown here. Learn more in the NVIDIA Documentation.Get detailed NIM model metadata, including properties, deployment, and configuration, via the NIM Metadata API.

		Engine					Actions
h200_nvl	bf16	tensorrt_llm	1	—	—	—	Copy NIM CLI Verification
gh200_144gb	fp8	tensorrt_llm	1	—	—	—	Copy NIM CLI Verification
gb200	fp8	tensorrt_llm	2	—	—	—	Copy NIM CLI Verification
l40s	fp8	tensorrt_llm	2	—	—	—	Copy NIM CLI Verification
h200_nvl	bf16	tensorrt_llm	2	—	—	—	Copy NIM CLI Verification
h200	fp8	tensorrt_llm	2	—	—	—	Copy NIM CLI Verification
rtx6000_blackwell_sv	bf16	tensorrt_llm	1	—	—	—	Copy NIM CLI Verification
h200	bf16	tensorrt_llm	1	—	—	—	Copy NIM CLI Verification
a100_sxm4_40gb	bf16	tensorrt_llm	2	—	—	—	Copy NIM CLI Verification
h200	bf16	tensorrt_llm	1	—	—	—	Copy NIM CLI Verification