mixtral-8x7b-instruct-v0-1

NVIDIA

Container

NVIDIA

mixtral-8x7b-instruct-v0-1

This container houses the Mixtral-8x7B-Instruct-v0.1, a sophisticated, instruction-tuned model from Mistral AI. It uses a Sparse Mixture of Experts (SMoE) architecture, dynamically selecting 2 of its 8 experts per token for greater efficiency.

NVIDIA NIM

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.

			Profile	Engine		Actions
A100 SXM4 80GB	20b2:10de	bf16	throughput	tensorrt_llm	2	Copy NIM CLI Verification
A10G	2237:10de	bf16	latency	tensorrt_llm	8	Copy NIM CLI Verification
B200	2901:10de	fp8	latency	tensorrt_llm	2	Copy NIM CLI Verification
H200 NVL	233b:10de	bf16	throughput	tensorrt_llm	1	Copy NIM CLI Verification
H100 80GB HBM3	2330:10de	fp8	throughput	tensorrt_llm	1	Copy NIM CLI Verification
H100 80GB HBM3	2330:10de	fp8	latency	tensorrt_llm	2	Copy NIM CLI Verification
B200	2901:10de	bf16	throughput	tensorrt_llm	1	Copy NIM CLI Verification
L40S	26b9:10de	bf16	latency	tensorrt_llm	4	Copy NIM CLI Verification
H200 NVL	233b:10de	fp8	latency	tensorrt_llm	2	Copy NIM CLI Verification
H100 NVL	2321:10de	bf16	throughput	tensorrt_llm	1	Copy NIM CLI Verification