nvidia/DeepSeek-R1-0528-NVFP4
Text Generation
•
397B
•
Updated
•
22k
•
39
Inference Optimized Checkpoints (with Model Optimizer)
A collection of generative models quantized and optimized for inference with Model Optimizer.
-
-
nvidia/DeepSeek-R1-0528-NVFP4-v2
Text Generation • 394B • Updated • 144k • 10 -
nvidia/Kimi-K2-Thinking-NVFP4
Text Generation • Updated • 2.56k • 14 -
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8
Text Generation • 32B • Updated • 64.5k • 141 -
nvidia/Llama-3.3-70B-Instruct-NVFP4
41B • Updated • 24.2k • 26 -
nvidia/Llama-3.3-70B-Instruct-FP8
71B • Updated • 27k • 14 -
nvidia/Llama-3.1-8B-Instruct-NVFP4
5B • Updated • 13.9k • 4 -
nvidia/Llama-3.1-8B-Instruct-FP8
Text Generation • 8B • Updated • 35.4k • • 31 -
nvidia/Qwen3-235B-A22B-NVFP4
Text Generation • 133B • Updated • 3.22k • 8 -
nvidia/Qwen3-235B-A22B-FP8
Text Generation • 235B • Updated • 1.38k • 2 -
nvidia/Qwen3-30B-A3B-NVFP4
Text Generation • 16B • Updated • 38.5k • 17 -
nvidia/Qwen3-32B-NVFP4
Text Generation • 17B • Updated • 2.16k • 3 -
nvidia/Qwen3-14B-NVFP4
Text Generation • 8B • Updated • 4.58k • 4 -
nvidia/Qwen3-14B-FP8
Text Generation • 15B • Updated • 3.53k • 2 -
nvidia/Qwen3-8B-NVFP4
Text Generation • 5B • Updated • 6.37k • 7 -
nvidia/Qwen3-8B-FP8
Text Generation • 8B • Updated • 6.89k • 2 -
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8
Text Generation • 50B • Updated • 2.82k • 23 -
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8
Text Generation • 253B • Updated • 300 • 10 -
nvidia/Llama-4-Scout-17B-16E-Instruct-NVFP4
56B • Updated • 37.1k • 13 -
nvidia/Llama-4-Scout-17B-16E-Instruct-FP8
109B • Updated • 278k • 9 -
nvidia/Llama-4-Maverick-17B-128E-Instruct-FP8
402B • Updated • 3.51k • 11 -
nvidia/Phi-4-reasoning-plus-FP8
15B • Updated • 468 • 3 -
nvidia/Qwen2.5-VL-7B-Instruct-NVFP4
Text Generation • 5B • Updated • 970 • 7 -
black-forest-labs/FLUX.1-dev-onnx
Text-to-Image • Updated • 102 -
nvidia/DeepSeek-R1-NVFP4
Text Generation • 397B • Updated • 23.8k • 267 -
nvidia/DeepSeek-R1-NVFP4-v2
Text Generation • 394B • Updated • 1.22k • 5 -
nvidia/DeepSeek-V3-0324-NVFP4
Text Generation • 397B • Updated • 90.8k • 14 -
nvidia/Llama-3_3-Nemotron-Super-49B-v1-FP8
Text Generation • 50B • Updated • 256 • 11 -
nvidia/Llama-3.1-70B-Instruct-FP8
Text Generation • 71B • Updated • 5.07k • • 14 -
nvidia/Llama-3.1-405B-Instruct-FP8
Text Generation • 406B • Updated • 2.37k • 14 -
nvidia/Llama-3.1-405B-Instruct-NVFP4
230B • Updated • 1.32k • 6 -
nvidia/Phi-4-multimodal-instruct-NVFP4
4B • Updated • 1.87k • 6 -
nvidia/Phi-4-multimodal-instruct-FP8
6B • Updated • 2.12k • 4 -
nvidia/Phi-4-reasoning-plus-NVFP4
8B • Updated • 550 • 6 -
nvidia/Qwen2.5-VL-7B-Instruct-FP8
Text Generation • 8B • Updated • 4.86k • 6 -
nvidia/DeepSeek-V3.1-NVFP4
Text Generation • 394B • Updated • 1.83k • 11