nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash
Text Generation • 0.7B • Updated • 1.7k • 23
Speculative Decoding Modules
A collection of speculative decoding modules created using Model Optimizer.
-
-
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark
Text Generation • 0.8B • Updated • 75k • 43 -
nvidia/Kimi-K2.5-Thinking-Eagle3
Text Generation • 2B • Updated • 1.06k • 21 -
nvidia/Kimi-K2-Thinking-Eagle3
Text Generation • 2B • Updated • 254 • 2 -
nvidia/gpt-oss-120b-Eagle3-short-context
Text Generation • 0.8B • Updated • 191k • 23 -
nvidia/gpt-oss-120b-Eagle3-long-context
Text Generation • 0.2B • Updated • 1.57k • 92 -
nvidia/gpt-oss-120b-Eagle3-throughput
Text Generation • 0.8B • Updated • 747 • 38 -
nvidia/Qwen3-235B-A22B-Eagle3
Text Generation • 0.3B • Updated • 628 • 18 -
nvidia/Llama-4-Maverick-17B-128E-Eagle3
2B • Updated • 1 • 11 -
nvidia/Qwen3-235B-A22B-Thinking-2507-Eagle3
Text Generation • 0.3B • Updated • 254 • 2 -
nvidia/Qwen3-235B-A22B-Thinking-2507-FP4-Eagle3
Text Generation • 0.9B • Updated • 216 • 1 -
nvidia/Qwen3-30B-A3B-Thinking-2507-Eagle3
Text Generation • 0.1B • Updated • 436 • 7 -
nvidia/Llama-3.1-8B-Medusa-FP8
10B • Updated • 209 • 12 -
nvidia/Llama-3.3-70B-Instruct-Eagle3
Text Generation • 2B • Updated • 728 • 5 -
nvidia/Kimi-K2.6-Eagle3
Text Generation • 2B • Updated • 1.17k • 17 -
nvidia/MiniMax-M3-DSpark
Text Generation • 3B • Updated • 802 • 18 -
nvidia/DeepSeek-V4-Pro-nvfp4-DSpark
Text Generation • 1.7T • Updated • 733 • 7 -
nvidia/DeepSeek-V4-Flash-nvfp4-DSpark
Text Generation • 304B • Updated • 817 • 33 -
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4-LiLiCorr
Text Generation • 1.0B • Updated • 5.77k • 11