nvidia/gpt-oss-120b-Eagle3-short-context
Text Generation • Updated
• 33.7k • 15
Speculative Decoding Modules
A collection of speculative decoding modules created using Model Optimizer.
-
-
nvidia/gpt-oss-120b-Eagle3-long-context
Text Generation • 0.2B • Updated • 19.6k • 60 -
nvidia/gpt-oss-120b-Eagle3-throughput
Text Generation • Updated • 203 • 33 -
nvidia/Qwen3-235B-A22B-Eagle3
Text Generation • 0.3B • Updated • 3.62k • 10 -
nvidia/Llama-4-Maverick-17B-128E-Eagle3
Updated • 6 • 9 -
nvidia/Llama-3.1-8B-Medusa-FP8
10B • Updated • 22 • 10 -
nvidia/Llama-3.3-70B-Instruct-Eagle3
Text Generation • Updated • 152 • 2