nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4
Text Generation • 67B • Updated • 881k • 299
Inference Optimized Checkpoints (with Model Optimizer)
A collection of generative models quantized and optimized for inference with Model Optimizer.
-
-
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4
Text Generation • 18B • Updated • 343k • 150 -
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
Text Generation • 124B • Updated • 370k • 244 -
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8
Text Generation • 32B • Updated • 856k • • 340 -
nvidia/Kimi-K2.5-NVFP4
Text Generation • Updated • 1.45M • 81 -
nvidia/Qwen3.5-397B-A17B-NVFP4
Text Generation • Updated • 575k • 97 -
nvidia/GLM-5-NVFP4
Text Generation • 435B • Updated • 95.7k • 31 -
nvidia/MiniMax-M2.7-NVFP4
Text Generation • 116B • Updated • 91.2k • 34 -
nvidia/MiniMax-M2.5-NVFP4
Text Generation • 116B • Updated • 98.4k • 34 -
nvidia/Gemma-4-31B-IT-NVFP4
Text Generation • 21B • Updated • 2.29M • 466 -
nvidia/Gemma-4-26B-A4B-NVFP4
Text Generation • 14B • Updated • 411k • 39 -
nvidia/DeepSeek-R1-0528-NVFP4-v2
Text Generation • 394B • Updated • 1.52M • 23 -
nvidia/Kimi-K2-Thinking-NVFP4
Text Generation • Updated • 12.1k • 30 -
nvidia/Qwen3-Next-80B-A3B-Thinking-NVFP4
Text Generation • Updated • 3.47k • 59 -
nvidia/Qwen3-Next-80B-A3B-Instruct-NVFP4
Text Generation • Updated • 19.7k • 39 -
nvidia/Llama-3.3-70B-Instruct-NVFP4
Updated • 114k • 42 -
nvidia/Llama-3.3-70B-Instruct-FP8
71B • Updated • 38.6k • 23 -
nvidia/Qwen3-235B-A22B-FP8
Text Generation • 235B • Updated • 1.7k • 5 -
nvidia/Llama-3.1-8B-Instruct-NVFP4
5B • Updated • 188k • 10 -
nvidia/Llama-3.1-8B-Instruct-FP8
Text Generation • 8B • Updated • 670k • • 35 -
nvidia/Qwen3-30B-A3B-NVFP4
Text Generation • 16B • Updated • 151k • 30 -
nvidia/DeepSeek-R1-0528-NVFP4
Text Generation • 397B • Updated • 5.99k • 44 -
nvidia/Qwen3-235B-A22B-NVFP4
Text Generation • 133B • Updated • 3.27k • 18 -
nvidia/Qwen3-32B-NVFP4
Text Generation • 17B • Updated • 83.6k • 16 -
nvidia/Qwen3-14B-NVFP4
Text Generation • 8B • Updated • 10.6k • 10 -
nvidia/Qwen3-14B-FP8
Text Generation • 15B • Updated • 3.24k • 5 -
nvidia/Qwen3-8B-NVFP4
Text Generation • 5B • Updated • 49.5k • 17 -
nvidia/Qwen3-8B-FP8
Text Generation • 8B • Updated • 18.9k • 5 -
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8
Text Generation • 50B • Updated • 87k • 28 -
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8
Text Generation • 253B • Updated • 2.54k • 12 -
nvidia/Llama-4-Scout-17B-16E-Instruct-NVFP4
56B • Updated • 86.4k • 31 -
nvidia/Llama-4-Scout-17B-16E-Instruct-FP8
109B • Updated • 253k • 15 -
nvidia/Llama-4-Maverick-17B-128E-Instruct-FP8
402B • Updated • 1.18k • 14 -
nvidia/Phi-4-reasoning-plus-FP8
15B • Updated • 404 • 6 -
nvidia/Qwen2.5-VL-7B-Instruct-NVFP4
Text Generation • 5B • Updated • 149k • 15 -
black-forest-labs/FLUX.1-dev-onnx
Text-to-Image • Updated • 108 -
nvidia/DeepSeek-R1-NVFP4
Text Generation • 397B • Updated • 9.61k • 278 -
nvidia/DeepSeek-R1-NVFP4-v2
Text Generation • 394B • Updated • 2.66k • 7 -
nvidia/DeepSeek-V3-0324-NVFP4
Text Generation • 397B • Updated • 49.3k • 17 -
nvidia/Llama-3_3-Nemotron-Super-49B-v1-FP8
Text Generation • 50B • Updated • 2.8k • 13 -
nvidia/Llama-3.1-70B-Instruct-FP8
Text Generation • 71B • Updated • 8.08k • 18 -
nvidia/Llama-3.1-405B-Instruct-FP8
Text Generation • 406B • Updated • 19.8k • 16 -
nvidia/Llama-3.1-405B-Instruct-NVFP4
Updated • 2.78k • 12 -
nvidia/Phi-4-multimodal-instruct-NVFP4
4B • Updated • 2.7k • 11 -
nvidia/Phi-4-multimodal-instruct-FP8
6B • Updated • 863 • 7 -
nvidia/Phi-4-reasoning-plus-NVFP4
8B • Updated • 1.18k • 9 -
nvidia/Qwen2.5-VL-7B-Instruct-FP8
Text Generation • 8B • Updated • 1.29k • 8 -
nvidia/DeepSeek-V3.1-NVFP4
Text Generation • 394B • Updated • 14.4k • 16 -
nvidia/DeepSeek-V3.2-NVFP4
Text Generation • 394B • Updated • 52.6k • 15 -
nvidia/Qwen3-Coder-480B-A35B-Instruct-NVFP4
Text Generation • 241B • Updated • 911 • 12 -
nvidia/Qwen3-235B-A22B-Thinking-2507-NVFP4
Text Generation • Updated • 970 • 9 -
nvidia/Qwen3-235B-A22B-Instruct-2507-NVFP4
Text Generation • 120B • Updated • 6.2k • 9 -
nvidia/GLM-4.7-NVFP4
Text Generation • 183B • Updated • 5.22k • 15 -
nvidia/Qwen3-VL-235B-A22B-Instruct-NVFP4
119B • Updated • 849 • 3 -
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4
Any-to-Any • 18B • Updated • 663k • 96 -
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8
Any-to-Any • 33B • Updated • 113k • 45