nvidia/DeepSeek-R1-0528-NVFP4
Text Generation
•
397B
•
Updated
•
43.7k
•
39
Inference Optimized Checkpoints (with Model Optimizer)
A collection of generative models quantized and optimized for inference with TensorRT Model Optimizer.
-
-
nvidia/DeepSeek-R1-0528-NVFP4-v2
Text Generation • 394B • Updated • 93.6k • 10 -
nvidia/Llama-3.3-70B-Instruct-NVFP4
41B • Updated • 33.1k • 25 -
nvidia/Llama-3.3-70B-Instruct-FP8
71B • Updated • 27.5k • 13 -
nvidia/Llama-3.1-8B-Instruct-NVFP4
5B • Updated • 18.9k • 3 -
nvidia/Llama-3.1-8B-Instruct-FP8
Text Generation • 8B • Updated • 36.8k • • 31 -
nvidia/Qwen3-235B-A22B-NVFP4
Text Generation • 133B • Updated • 3.59k • 5 -
nvidia/Qwen3-235B-A22B-FP8
Text Generation • Updated • 981 • 1 -
nvidia/Qwen3-30B-A3B-NVFP4
Text Generation • 16B • Updated • 4.34k • 16 -
nvidia/Qwen3-32B-NVFP4
Text Generation • 17B • Updated • 2.5k • 2 -
nvidia/Qwen3-14B-NVFP4
Text Generation • 8B • Updated • 5.94k • 3 -
nvidia/Qwen3-14B-FP8
Text Generation • 15B • Updated • 3.4k • 1 -
nvidia/Qwen3-8B-NVFP4
Text Generation • 5B • Updated • 6.41k • 5 -
nvidia/Qwen3-8B-FP8
Text Generation • 8B • Updated • 4.56k • 1 -
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8
Text Generation • 50B • Updated • 5.16k • 21 -
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8
Text Generation • 253B • Updated • 515 • 9 -
nvidia/Llama-4-Scout-17B-16E-Instruct-NVFP4
56B • Updated • 30.9k • 7 -
nvidia/Llama-4-Scout-17B-16E-Instruct-FP8
109B • Updated • 208k • 7 -
nvidia/Llama-4-Maverick-17B-128E-Instruct-FP8
402B • Updated • 3.97k • 11 -
nvidia/Phi-4-reasoning-plus-FP8
15B • Updated • 593 • 2 -
nvidia/Qwen2.5-VL-7B-Instruct-NVFP4
Text Generation • 5B • Updated • 2.5k • 4 -
black-forest-labs/FLUX.1-dev-onnx
Text-to-Image • Updated • 100 -
nvidia/DeepSeek-R1-NVFP4
Text Generation • 397B • Updated • 1.82k • 266 -
nvidia/DeepSeek-R1-NVFP4-v2
Text Generation • 394B • Updated • 1.52k • 4 -
nvidia/DeepSeek-V3-0324-NVFP4
Text Generation • 397B • Updated • 39.6k • 13 -
nvidia/Llama-3_3-Nemotron-Super-49B-v1-FP8
Text Generation • 50B • Updated • 191 • 10 -
nvidia/Llama-3.1-70B-Instruct-FP8
Text Generation • 71B • Updated • 4.52k • • 14 -
nvidia/Llama-3.1-405B-Instruct-FP8
Text Generation • 406B • Updated • 2.83k • 14 -
nvidia/Llama-3.1-405B-Instruct-NVFP4
230B • Updated • 2.87k • 6 -
nvidia/Phi-4-multimodal-instruct-NVFP4
4B • Updated • 1.15k • 5 -
nvidia/Phi-4-multimodal-instruct-FP8
6B • Updated • 846 • 3 -
nvidia/Phi-4-reasoning-plus-NVFP4
8B • Updated • 475 • 5 -
nvidia/Qwen2.5-VL-7B-Instruct-FP8
Text Generation • 8B • Updated • 422 • 4 -
nvidia/DeepSeek-V3.1-NVFP4
Text Generation • 394B • Updated • 54 • 8