nvidia/DeepSeek-R1-0528-NVFP4
Text Generation
•
397B
•
Updated
•
76.8k
•
38
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 • 75.5k • 9 -
nvidia/Llama-3.3-70B-Instruct-NVFP4
41B • Updated • 40.1k • 24 -
nvidia/Llama-3.3-70B-Instruct-FP8
71B • Updated • 34.1k • 12 -
nvidia/Llama-3.1-8B-Instruct-NVFP4
5B • Updated • 18.2k • 2 -
nvidia/Llama-3.1-8B-Instruct-FP8
Text Generation • 8B • Updated • 36.2k • • 30 -
nvidia/Qwen3-235B-A22B-NVFP4
Text Generation • 133B • Updated • 4.01k • 3 -
nvidia/Qwen3-235B-A22B-FP8
Text Generation • Updated • 1.23k -
nvidia/Qwen3-30B-A3B-NVFP4
Text Generation • 16B • Updated • 5.32k • 15 -
nvidia/Qwen3-32B-NVFP4
Text Generation • 17B • Updated • 2.4k • 1 -
nvidia/Qwen3-14B-NVFP4
Text Generation • 8B • Updated • 6.53k • 2 -
nvidia/Qwen3-14B-FP8
Text Generation • 15B • Updated • 3.89k -
nvidia/Qwen3-8B-NVFP4
Text Generation • 5B • Updated • 6.76k • 4 -
nvidia/Qwen3-8B-FP8
Text Generation • 8B • Updated • 4.77k -
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8
Text Generation • 50B • Updated • 4.94k • 20 -
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8
Text Generation • 253B • Updated • 455 • 8 -
nvidia/Llama-4-Scout-17B-16E-Instruct-NVFP4
56B • Updated • 27.5k • 5 -
nvidia/Llama-4-Scout-17B-16E-Instruct-FP8
109B • Updated • 190k • 6 -
nvidia/Llama-4-Maverick-17B-128E-Instruct-FP8
402B • Updated • 4.33k • 10 -
nvidia/Phi-4-reasoning-plus-FP8
15B • Updated • 690 • 1 -
nvidia/Qwen2.5-VL-7B-Instruct-NVFP4
Text Generation • 5B • Updated • 2.46k • 3 -
black-forest-labs/FLUX.1-dev-onnx
Text-to-Image • Updated • 99 -
nvidia/DeepSeek-R1-NVFP4
Text Generation • 397B • Updated • 2.47k • 265 -
nvidia/DeepSeek-R1-NVFP4-v2
Text Generation • 394B • Updated • 1.32k • 3 -
nvidia/DeepSeek-V3-0324-NVFP4
Text Generation • 397B • Updated • 28k • 12 -
nvidia/Llama-3_3-Nemotron-Super-49B-v1-FP8
Text Generation • 50B • Updated • 215 • 9 -
nvidia/Llama-3.1-70B-Instruct-FP8
Text Generation • 71B • Updated • 4.84k • • 13 -
nvidia/Llama-3.1-405B-Instruct-FP8
Text Generation • 406B • Updated • 3.37k • 13 -
nvidia/Llama-3.1-405B-Instruct-NVFP4
230B • Updated • 2.9k • 5 -
nvidia/Phi-4-multimodal-instruct-NVFP4
4B • Updated • 612 • 4 -
nvidia/Phi-4-multimodal-instruct-FP8
6B • Updated • 520 • 2 -
nvidia/Phi-4-reasoning-plus-NVFP4
8B • Updated • 549 • 4 -
nvidia/Qwen2.5-VL-7B-Instruct-FP8
Text Generation • 8B • Updated • 449 • 3