nvidia/DeepSeek-R1-0528-FP4
Text Generation
•
Updated
•
69.2k
•
36
Inference Optimized Checkpoints (with Model Optimizer)
A collection of generative models quantized and optimized for inference with TensorRT Model Optimizer.
-
-
nvidia/DeepSeek-R1-0528-FP4-v2
Text Generation • 394B • Updated • 12.3k • 7 -
nvidia/Llama-3.3-70B-Instruct-FP4
41B • Updated • 18.1k • 22 -
nvidia/Llama-3.3-70B-Instruct-FP8
71B • Updated • 175k • 8 -
nvidia/Llama-3.1-8B-Instruct-FP4
5B • Updated • 3.04k -
nvidia/Llama-3.1-8B-Instruct-FP8
Text Generation • 8B • Updated • 130k • • 29 -
nvidia/Qwen3-235B-A22B-FP4
Text Generation • Updated • 592 -
nvidia/Qwen3-235B-A22B-FP8
Text Generation • Updated • 132 -
nvidia/Qwen3-30B-A3B-FP4
Text Generation • 16B • Updated • 4.03k • 6 -
nvidia/Qwen3-32B-FP4
Text Generation • 17B • Updated • 241 -
nvidia/Qwen3-14B-FP4
Text Generation • 8B • Updated • 4.29k -
nvidia/Qwen3-14B-FP8
Text Generation • 15B • Updated • 273 -
nvidia/Qwen3-8B-FP4
Text Generation • 5B • Updated • 79k • 2 -
nvidia/Qwen3-8B-FP8
Text Generation • 8B • Updated • 626 -
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8
Text Generation • 50B • Updated • 3.29k • 18 -
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8
Text Generation • 253B • Updated • 916 • 8 -
nvidia/Llama-4-Scout-17B-16E-Instruct-FP4
56B • Updated • 22.7k • 2 -
nvidia/Llama-4-Scout-17B-16E-Instruct-FP8
109B • Updated • 20.5k • 6 -
nvidia/Llama-4-Maverick-17B-128E-Instruct-FP8
402B • Updated • 627 • 9 -
black-forest-labs/FLUX.1-dev-onnx
Text-to-Image • Updated • 94 -
nvidia/DeepSeek-R1-FP4
Text Generation • Updated • 7.57k • 263 -
nvidia/DeepSeek-R1-FP4-v2
Text Generation • 394B • Updated • 685 • 3 -
nvidia/DeepSeek-V3-0324-FP4
Text Generation • Updated • 17.8k • 12 -
nvidia/Llama-3_3-Nemotron-Super-49B-v1-FP8
Text Generation • 50B • Updated • 947 • 9 -
nvidia/Llama-3.1-70B-Instruct-FP8
Text Generation • 71B • Updated • 6.71k • • 12 -
nvidia/Llama-3.1-405B-Instruct-FP8
Text Generation • 406B • Updated • 3.6k • 11 -
nvidia/Llama-3.1-405B-Instruct-FP4
230B • Updated • 1.4k • 5 -
nvidia/Phi-4-multimodal-instruct-FP4
4B • Updated • 251 • 3 -
nvidia/Phi-4-multimodal-instruct-FP8
6B • Updated • 323 -
nvidia/Phi-4-reasoning-plus-FP4
8B • Updated • 345 • 3 -
nvidia/Phi-4-reasoning-plus-FP8
15B • Updated • 111k -
nvidia/Qwen2.5-VL-7B-Instruct-FP4
Text Generation • 5B • Updated • 49.1k • 3 -
nvidia/Qwen2.5-VL-7B-Instruct-FP8
Text Generation • 8B • Updated • 423 • 2